From 419735f4401fd7a96b1b6fe2b87ddbc8b11cfe85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eren=20G=C3=B6lge?= Date: Sun, 6 Jun 2021 13:39:52 +0200 Subject: [PATCH] refactor and fix multi-speaker training in Trainer and Tacotron models --- TTS/tts/datasets/TTSDataset.py | 4 +- TTS/tts/datasets/formatters.py | 15 + TTS/tts/models/tacotron.py | 7 +- TTS/tts/models/tacotron2.py | 10 +- TTS/tts/utils/speakers.py | 33 +- tests/data/ljspeech/speakers.json | 2612 +++++++++++++++++ tests/data_tests/__init__.py | 0 tests/inference_tests/__init__.py | 0 tests/test_speaker_manager.py | 6 +- tests/text_tests/__init__.py | 0 .../test_tacotron2_d-vectors_train.py | 57 + .../test_tacotron2_speaker_emb_train.py | 55 + 12 files changed, 2779 insertions(+), 20 deletions(-) create mode 100644 tests/data/ljspeech/speakers.json create mode 100644 tests/data_tests/__init__.py create mode 100644 tests/inference_tests/__init__.py create mode 100644 tests/text_tests/__init__.py create mode 100644 tests/tts_tests/test_tacotron2_d-vectors_train.py create mode 100644 tests/tts_tests/test_tacotron2_speaker_emb_train.py diff --git a/TTS/tts/datasets/TTSDataset.py b/TTS/tts/datasets/TTSDataset.py index 2522b55a..d0fbb553 100644 --- a/TTS/tts/datasets/TTSDataset.py +++ b/TTS/tts/datasets/TTSDataset.py @@ -301,12 +301,12 @@ class TTSDataset(Dataset): # get pre-computed d-vectors if self.d_vector_mapping is not None: wav_files_names = [batch[idx]["wav_file_name"] for idx in ids_sorted_decreasing] - d_vectors = [self.speaker_mapping[w]["embedding"] for w in wav_files_names] + d_vectors = [self.d_vector_mapping[w]["embedding"] for w in wav_files_names] else: d_vectors = None # get numerical speaker ids from speaker names if self.speaker_id_mapping: - speaker_ids = [self.speaker_manager.speaker_ids[sn] for sn in speaker_names] + speaker_ids = [self.speaker_id_mapping[sn] for sn in speaker_names] else: speaker_ids = None # compute features diff --git a/TTS/tts/datasets/formatters.py b/TTS/tts/datasets/formatters.py index 815a1b1d..3cb37168 100644 --- a/TTS/tts/datasets/formatters.py +++ b/TTS/tts/datasets/formatters.py @@ -107,6 +107,21 @@ def ljspeech(root_path, meta_file): return items +def ljspeech_test(root_path, meta_file): + """Normalizes the LJSpeech meta data file for TTS testing + https://keithito.com/LJ-Speech-Dataset/""" + txt_file = os.path.join(root_path, meta_file) + items = [] + speaker_name = "ljspeech" + with open(txt_file, "r", encoding="utf-8") as ttf: + for idx, line in enumerate(ttf): + cols = line.split("|") + wav_file = os.path.join(root_path, "wavs", cols[0] + ".wav") + text = cols[1] + items.append([text, wav_file, f"ljspeech-{idx}"]) + return items + + def sam_accenture(root_path, meta_file): """Normalizes the sam-accenture meta data file to TTS format https://github.com/Sam-Accenture-Non-Binary-Voice/non-binary-voice-files""" diff --git a/TTS/tts/models/tacotron.py b/TTS/tts/models/tacotron.py index 5eeeedaa..3ee70431 100644 --- a/TTS/tts/models/tacotron.py +++ b/TTS/tts/models/tacotron.py @@ -262,7 +262,12 @@ class Tacotron(TacotronAbstract): if self.num_speakers > 1: if not self.use_d_vectors: # B x 1 x speaker_embed_dim - embedded_speakers = self.speaker_embedding(cond_input["speaker_ids"])[:, None] + embedded_speakers = self.speaker_embedding(cond_input["speaker_ids"]) + # reshape embedded_speakers + if embedded_speakers.ndim == 1: + embedded_speakers = embedded_speakers[None, None, :] + elif embedded_speakers.ndim == 2: + embedded_speakers = embedded_speakers[None, :] else: # B x 1 x speaker_embed_dim embedded_speakers = torch.unsqueeze(cond_input["d_vectors"], 1) diff --git a/TTS/tts/models/tacotron2.py b/TTS/tts/models/tacotron2.py index b6da4e44..f6e59542 100644 --- a/TTS/tts/models/tacotron2.py +++ b/TTS/tts/models/tacotron2.py @@ -261,9 +261,13 @@ class Tacotron2(TacotronAbstract): # B x gst_dim encoder_outputs = self.compute_gst(encoder_outputs, cond_input["style_mel"], cond_input["d_vectors"]) if self.num_speakers > 1: - if not self.embeddings_per_sample: - x_vector = self.speaker_embedding(cond_input['speaker_ids'])[:, None] - x_vector = torch.unsqueeze(x_vector, 0).transpose(1, 2) + if not self.use_d_vectors: + embedded_speakers = self.speaker_embedding(cond_input["speaker_ids"])[None] + # reshape embedded_speakers + if embedded_speakers.ndim == 1: + embedded_speakers = embedded_speakers[None, None, :] + elif embedded_speakers.ndim == 2: + embedded_speakers = embedded_speakers[None, :] else: embedded_speakers = cond_input["d_vectors"] diff --git a/TTS/tts/utils/speakers.py b/TTS/tts/utils/speakers.py index 0f43bf97..01e26c6b 100755 --- a/TTS/tts/utils/speakers.py +++ b/TTS/tts/utils/speakers.py @@ -11,9 +11,16 @@ from TTS.speaker_encoder.utils.generic_utils import setup_model from TTS.utils.audio import AudioProcessor -def make_speakers_json_path(out_path): - """Returns conventional speakers.json location.""" - return os.path.join(out_path, "speakers.json") +def _set_file_path(path): + """Find the speakers.json under the given path or the above it. + Intended to band aid the different paths returned in restored and continued training.""" + path_restore = os.path.join(os.path.dirname(path), "speakers.json") + path_continue = os.path.join(path, "speakers.json") + if os.path.exists(path_restore): + return path_restore + if os.path.exists(path_continue): + return path_continue + raise FileNotFoundError(f" [!] `speakers.json` not found in {path}") def load_speaker_mapping(out_path): @@ -21,7 +28,7 @@ def load_speaker_mapping(out_path): if os.path.splitext(out_path)[1] == ".json": json_file = out_path else: - json_file = make_speakers_json_path(out_path) + json_file = _set_file_path(out_path) with open(json_file) as f: return json.load(f) @@ -29,7 +36,7 @@ def load_speaker_mapping(out_path): def save_speaker_mapping(out_path, speaker_mapping): """Saves speaker mapping if not yet present.""" if out_path is not None: - speakers_json_path = make_speakers_json_path(out_path) + speakers_json_path = _set_file_path(out_path) with open(speakers_json_path, "w") as f: json.dump(speaker_mapping, f, indent=4) @@ -40,10 +47,10 @@ def get_speaker_manager(c, restore_path, meta_data_train, out_path=None): if c.use_speaker_embedding: speaker_manager.set_speaker_ids_from_data(meta_data_train) if restore_path: + speakers_file = _set_file_path(restore_path) # restoring speaker manager from a previous run. if c.use_external_speaker_embedding_file: # restore speaker manager with the embedding file - speakers_file = os.path.dirname(restore_path) if not os.path.exists(speakers_file): print( "WARNING: speakers.json was not found in restore_path, trying to use CONFIG.external_speaker_embedding_file" @@ -55,7 +62,6 @@ def get_speaker_manager(c, restore_path, meta_data_train, out_path=None): speaker_manager.load_d_vectors_file(c.external_speaker_embedding_file) speaker_manager.set_d_vectors_from_file(speakers_file) elif not c.use_external_speaker_embedding_file: # restor speaker manager with speaker ID file. - speakers_file = os.path.dirname(restore_path) speaker_ids_from_data = speaker_manager.speaker_ids speaker_manager.set_speaker_ids_from_file(speakers_file) assert all( @@ -75,8 +81,8 @@ def get_speaker_manager(c, restore_path, meta_data_train, out_path=None): ) # save file if path is defined if out_path: - out_file_path = os.path.join(out_path, "speaker.json") - print(" > Saving `speaker.json` to {out_file_path}.") + out_file_path = os.path.join(out_path, "speakers.json") + print(f" > Saving `speakers.json` to {out_file_path}.") if c.use_external_speaker_embedding_file and c.external_speaker_embedding_file: speaker_manager.save_d_vectors_to_file(out_file_path) else: @@ -138,7 +144,7 @@ class SpeakerManager: self.speaker_encoder_ap = None if data_items: - self.speaker_ids, _ = self.parse_speakers_from_data(self.data_items) + self.speaker_ids, self.speaker_names, _ = self.parse_speakers_from_data(self.data_items) if d_vectors_file_path: self.set_d_vectors_from_file(d_vectors_file_path) @@ -163,6 +169,10 @@ class SpeakerManager: def num_speakers(self): return len(self.speaker_ids) + @property + def speaker_names(self): + return list(self.speaker_ids.keys()) + @property def d_vector_dim(self): """Dimensionality of d_vectors. If d_vectors are not loaded, returns zero.""" @@ -224,7 +234,8 @@ class SpeakerManager: file_path (str): Path to the target json file. """ self.d_vectors = self._load_json(file_path) - self.speaker_ids = list(set(sorted(x["name"] for x in self.d_vectors.values()))) + speakers = sorted({x["name"] for x in self.d_vectors.values()}) + self.speaker_ids = {name: i for i, name in enumerate(speakers)} self.clip_ids = list(set(sorted(clip_name for clip_name in self.d_vectors.keys()))) def get_d_vector_by_clip(self, clip_idx: str) -> List: diff --git a/tests/data/ljspeech/speakers.json b/tests/data/ljspeech/speakers.json new file mode 100644 index 00000000..915cff73 --- /dev/null +++ b/tests/data/ljspeech/speakers.json @@ -0,0 +1,2612 @@ +{ + "LJ001-0001.wav": { + "name": "ljspeech-0", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0002.wav": { + "name": "ljspeech-1", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0003.wav": { + "name": "ljspeech-2", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0004.wav": { + "name": "ljspeech-3", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0005.wav": { + "name": "ljspeech-4", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0006.wav": { + "name": "ljspeech-5", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0007.wav": { + "name": "ljspeech-6", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0008.wav": { + "name": "ljspeech-7", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0009.wav": { + "name": "ljspeech-8", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + }, + "LJ001-0010.wav": { + "name": "ljspeech-9", + "embedding": [ + 0.05539746582508087, + 0.08493061363697052, + -0.010013150051236153, + 0.04369359463453293, + -0.05871078372001648, + 0.07792330533266068, + -0.12001194059848785, + 0.09205509722232819, + -0.053687505424022675, + 0.13110113143920898, + -0.0672345906496048, + 0.09076011180877686, + -0.012022187933325768, + -0.1773194968700409, + -0.03690509498119354, + 0.052139587700366974, + -0.06511855870485306, + -0.014169753529131413, + -0.0788075178861618, + -0.022713735699653625, + 0.026002388447523117, + 0.04142642393708229, + 0.06633599102497101, + -0.040966324508190155, + 0.05216488242149353, + 0.043708473443984985, + 0.008947450667619705, + 0.043884553015232086, + 0.015242422930896282, + -0.07271697372198105, + -0.03943272680044174, + 0.11445401608943939, + -0.01976911909878254, + -0.001584329642355442, + 0.03226276487112045, + -0.002877067308872938, + 0.006218053866177797, + -0.09210439026355743, + -0.023884698748588562, + 0.019102394580841064, + -0.023189997300505638, + 0.07678322494029999, + 0.04511963576078415, + -0.028598245233297348, + 0.02654365450143814, + -0.026303084567189217, + -0.036059144884347916, + -0.04994352161884308, + -0.10899694263935089, + 0.16808779537677765, + 0.0568464957177639, + 0.017774248495697975, + -0.0766686350107193, + -0.08056356757879257, + 0.11318203061819077, + -0.0009237118065357208, + -0.11983267217874527, + -0.04011853411793709, + 0.06481920927762985, + 0.18528658151626587, + -0.020618144422769547, + 0.0030966848134994507, + 0.030582068488001823, + 0.11048240959644318, + 0.026203282177448273, + 0.08886025100946426, + 0.0776662528514862, + 0.08468905836343765, + 0.02009391225874424, + 0.053141623735427856, + 0.04102938249707222, + 0.059041380882263184, + -0.006237464025616646, + -0.018360337242484093, + 0.015418153256177902, + -0.03559226542711258, + -0.05805520713329315, + -0.00861218199133873, + -0.021234268322587013, + -0.025556275621056557, + -0.012332704849541187, + -0.009777471423149109, + 0.03721384331583977, + 0.010376224294304848, + -0.05210898444056511, + 0.035450324416160583, + 0.0026437342166900635, + -0.03329150378704071, + 0.07028764486312866, + 0.03101171739399433, + 0.003101848065853119, + 0.029428653419017792, + -0.03445912152528763, + -0.11992329359054565, + -0.006469260435551405, + 0.02472860924899578, + -0.0021879260893911123, + 0.06576769798994064, + 0.04159736633300781, + -0.044104330241680145, + 0.10868340730667114, + 0.06065361574292183, + -0.00814537052065134, + 0.029497724026441574, + -0.0820949599146843, + 0.09694784879684448, + 0.10299994796514511, + 0.007466038689017296, + 0.0573151595890522, + -0.04003140702843666, + 0.0748046338558197, + 0.07954449951648712, + -0.14061805605888367, + -0.07225356996059418, + 0.030713198706507683, + -0.01169175747781992, + 0.015277700498700142, + 0.101996049284935, + 0.0023796744644641876, + 0.013835912570357323, + 0.08836984634399414, + -0.08798637241125107, + -0.053786784410476685, + -0.025867177173495293, + 0.07090725004673004, + -0.05228910967707634, + 0.024839768186211586, + 0.0543626993894577, + -0.048099253326654434, + -0.01027676835656166, + 0.04654526337981224, + -0.0034045036882162094, + 0.003895972855389118, + 0.04250902682542801, + -0.05232023075222969, + 0.06287448853254318, + -0.04146592691540718, + -0.0022073618602007627, + 0.07169511169195175, + 0.057035692036151886, + 0.04202979430556297, + -0.01752091944217682, + -0.03615778684616089, + -0.07597745209932327, + 0.0076013305224478245, + 0.03388708084821701, + 0.06191568076610565, + -0.01607775315642357, + 0.004401837941259146, + -0.06070601940155029, + -0.07674850523471832, + 0.059249889105558395, + -0.02222420647740364, + 0.10215721279382706, + -0.000883960397914052, + 0.010600706562399864, + 0.09869417548179626, + 0.011313805356621742, + -0.01187396701425314, + -0.04851905256509781, + -0.020747501403093338, + 0.043711841106414795, + 0.04022590070962906, + -0.06653523445129395, + -0.04014153778553009, + 0.012923783622682095, + 0.0024894566740840673, + -0.03801071271300316, + 0.017412755638360977, + 0.03090047463774681, + 0.021060986444354057, + 0.04588426649570465, + -0.061013057827949524, + 0.022323710843920708, + -0.0921829417347908, + -0.009262383915483952, + -0.0024641728959977627, + -0.04311069846153259, + -0.02953970432281494, + 0.11183556914329529, + 0.041883185505867004, + 0.01362229697406292, + -0.009713159874081612, + -0.07398185133934021, + -0.03448636084794998, + 0.06774093955755234, + 0.06281304359436035, + 0.005423923954367638, + 0.04070146754384041, + 0.04723779857158661, + 0.0025808606296777725, + 0.04067641496658325, + 0.0840836763381958, + 0.0662192553281784, + 6.253225728869438e-05, + -0.03287994861602783, + -0.07941965758800507, + 0.09294897317886353, + 0.08651109039783478, + -0.09662938117980957, + -0.08838298916816711, + -0.05120178312063217, + -0.06626439094543457, + 0.04893879592418671, + -0.017820902168750763, + -0.007398976478725672, + 0.02896031364798546, + -0.025766948238015175, + -0.10214102268218994, + -0.10014186799526215, + 0.1211889386177063, + -0.0510331466794014, + -0.02461140602827072, + -0.06880723685026169, + 0.02751768007874489, + 0.07350686937570572, + 0.038249749690294266, + -0.009252945892512798, + 0.013650302775204182, + 0.04884907230734825, + -0.08785197138786316, + 0.003136417828500271, + 0.05015810579061508, + -0.00904669426381588, + -0.10715165734291077, + 0.026881497353315353, + -0.07288249582052231, + 0.08610662072896957, + -0.06228051334619522, + 0.1673828363418579, + 0.006395484320819378, + -0.0426831915974617, + -0.08067314326763153, + 0.06747708469629288, + -0.049200400710105896, + 0.0475490465760231, + 0.05716557055711746, + 0.060844384133815765, + 0.04086177423596382, + -0.08346255123615265, + 0.0869344025850296, + 0.019769223406910896, + -0.020300764590501785, + -0.0708683505654335, + -0.030514180660247803, + -0.027429744601249695, + 0.021853724494576454, + -0.012019682675600052, + -0.0613793209195137, + 0.009929075837135315, + 0.0261012464761734, + -0.018161576241254807, + 0.07936893403530121, + 0.12791746854782104, + 0.08958099782466888, + -0.09469571709632874 + ] + } +} diff --git a/tests/data_tests/__init__.py b/tests/data_tests/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/tests/inference_tests/__init__.py b/tests/inference_tests/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/tests/test_speaker_manager.py b/tests/test_speaker_manager.py index a695fe61..baa50749 100644 --- a/tests/test_speaker_manager.py +++ b/tests/test_speaker_manager.py @@ -66,10 +66,10 @@ class SpeakerManagerTest(unittest.TestCase): print(manager.clip_ids) d_vector = manager.get_d_vector_by_clip(manager.clip_ids[0]) assert len(d_vector) == 256 - d_vectors = manager.get_d_vectors_by_speaker(manager.speaker_ids[0]) + d_vectors = manager.get_d_vectors_by_speaker(manager.speaker_names[0]) assert len(d_vectors[0]) == 256 - d_vector1 = manager.get_mean_d_vector(manager.speaker_ids[0], num_samples=2, randomize=True) + d_vector1 = manager.get_mean_d_vector(manager.speaker_names[0], num_samples=2, randomize=True) assert len(d_vector1) == 256 - d_vector2 = manager.get_mean_d_vector(manager.speaker_ids[0], num_samples=2, randomize=False) + d_vector2 = manager.get_mean_d_vector(manager.speaker_names[0], num_samples=2, randomize=False) assert len(d_vector2) == 256 assert np.sum(np.array(d_vector1) - np.array(d_vector2)) != 0 diff --git a/tests/text_tests/__init__.py b/tests/text_tests/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/tests/tts_tests/test_tacotron2_d-vectors_train.py b/tests/tts_tests/test_tacotron2_d-vectors_train.py new file mode 100644 index 00000000..7fda7e09 --- /dev/null +++ b/tests/tts_tests/test_tacotron2_d-vectors_train.py @@ -0,0 +1,57 @@ +import glob +import os +import shutil + +from tests import get_device_id, get_tests_output_path, run_cli +from TTS.tts.configs import Tacotron2Config + +config_path = os.path.join(get_tests_output_path(), "test_model_config.json") +output_path = os.path.join(get_tests_output_path(), "train_outputs") + +config = Tacotron2Config( + r=5, + batch_size=8, + eval_batch_size=8, + num_loader_workers=0, + num_val_loader_workers=0, + text_cleaner="english_cleaners", + use_phonemes=False, + phoneme_language="en-us", + phoneme_cache_path=os.path.join(get_tests_output_path(), "train_outputs/phoneme_cache/"), + run_eval=True, + test_delay_epochs=-1, + epochs=1, + print_step=1, + print_eval=True, + use_speaker_embedding=True, + use_external_speaker_embedding_file=True, + test_sentences=[ + "Be a voice, not an echo.", + ], + external_speaker_embedding_file="tests/data/ljspeech/speakers.json", + max_decoder_steps=50, +) + +config.audio.do_trim_silence = True +config.audio.trim_db = 60 +config.save_json(config_path) + +# train the model for one epoch +command_train = ( + f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_tts.py --config_path {config_path} " + f"--coqpit.output_path {output_path} " + "--coqpit.datasets.0.name ljspeech_test " + "--coqpit.datasets.0.meta_file_train metadata.csv " + "--coqpit.datasets.0.meta_file_val metadata.csv " + "--coqpit.datasets.0.path tests/data/ljspeech " + "--coqpit.test_delay_epochs 0 " +) +run_cli(command_train) + +# Find latest folder +continue_path = max(glob.glob(os.path.join(output_path, "*/")), key=os.path.getmtime) + +# restore the model and continue training for one more epoch +command_train = f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_tts.py --continue_path {continue_path} " +run_cli(command_train) +shutil.rmtree(continue_path) diff --git a/tests/tts_tests/test_tacotron2_speaker_emb_train.py b/tests/tts_tests/test_tacotron2_speaker_emb_train.py new file mode 100644 index 00000000..a242c724 --- /dev/null +++ b/tests/tts_tests/test_tacotron2_speaker_emb_train.py @@ -0,0 +1,55 @@ +import glob +import os +import shutil + +from tests import get_device_id, get_tests_output_path, run_cli +from TTS.tts.configs import Tacotron2Config + +config_path = os.path.join(get_tests_output_path(), "test_model_config.json") +output_path = os.path.join(get_tests_output_path(), "train_outputs") + +config = Tacotron2Config( + r=5, + batch_size=8, + eval_batch_size=8, + num_loader_workers=0, + num_val_loader_workers=0, + text_cleaner="english_cleaners", + use_phonemes=False, + phoneme_language="en-us", + phoneme_cache_path=os.path.join(get_tests_output_path(), "train_outputs/phoneme_cache/"), + run_eval=True, + test_delay_epochs=-1, + epochs=1, + print_step=1, + print_eval=True, + test_sentences=[ + "Be a voice, not an echo.", + ], + use_speaker_embedding=True, + max_decoder_steps=50, +) + +config.audio.do_trim_silence = True +config.audio.trim_db = 60 +config.save_json(config_path) + +# train the model for one epoch +command_train = ( + f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_tts.py --config_path {config_path} " + f"--coqpit.output_path {output_path} " + "--coqpit.datasets.0.name ljspeech_test " + "--coqpit.datasets.0.meta_file_train metadata.csv " + "--coqpit.datasets.0.meta_file_val metadata.csv " + "--coqpit.datasets.0.path tests/data/ljspeech " + "--coqpit.test_delay_epochs 0 " +) +run_cli(command_train) + +# Find latest folder +continue_path = max(glob.glob(os.path.join(output_path, "*/")), key=os.path.getmtime) + +# restore the model and continue training for one more epoch +command_train = f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_tts.py --continue_path {continue_path} " +run_cli(command_train) +shutil.rmtree(continue_path)