Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix pylint issues

This commit is contained in:
Edresson 2021-08-13 03:38:54 -03:00 committed by Eren Gölge
parent d91c595c5a
commit 5f1c18187f
4 changed files with 21 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
TTS/tts/datasets/formatters.py
View File

@ -12,7 +12,7 @@ from tqdm import tqdm
######################## ########################
def tweb(root_path, meta_file, **kwargs): def tweb(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalize TWEB dataset. """Normalize TWEB dataset.
https://www.kaggle.com/bryanpark/the-world-english-bible-speech-dataset https://www.kaggle.com/bryanpark/the-world-english-bible-speech-dataset
""" """
@ -28,7 +28,7 @@ def tweb(root_path, meta_file, **kwargs):
return items return items
def mozilla(root_path, meta_file, **kwargs): def mozilla(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalizes Mozilla meta data files to TTS format""" """Normalizes Mozilla meta data files to TTS format"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
items = [] items = []
@ -43,7 +43,7 @@ def mozilla(root_path, meta_file, **kwargs):
return items return items
def mozilla_de(root_path, meta_file, **kwargs): def mozilla_de(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalizes Mozilla meta data files to TTS format""" """Normalizes Mozilla meta data files to TTS format"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
items = [] items = []
@ -102,7 +102,7 @@ def mailabs(root_path, meta_files=None):
return items return items
def ljspeech(root_path, meta_file, **kwargs): def ljspeech(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalizes the LJSpeech meta data file to TTS format """Normalizes the LJSpeech meta data file to TTS format
https://keithito.com/LJ-Speech-Dataset/""" https://keithito.com/LJ-Speech-Dataset/"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
@ -117,7 +117,7 @@ def ljspeech(root_path, meta_file, **kwargs):
return items return items
def ljspeech_test(root_path, meta_file, **kwargs): def ljspeech_test(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalizes the LJSpeech meta data file for TTS testing """Normalizes the LJSpeech meta data file for TTS testing
https://keithito.com/LJ-Speech-Dataset/""" https://keithito.com/LJ-Speech-Dataset/"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
@ -131,7 +131,7 @@ def ljspeech_test(root_path, meta_file, **kwargs):
return items return items
def sam_accenture(root_path, meta_file, **kwargs): def sam_accenture(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalizes the sam-accenture meta data file to TTS format """Normalizes the sam-accenture meta data file to TTS format
https://github.com/Sam-Accenture-Non-Binary-Voice/non-binary-voice-files""" https://github.com/Sam-Accenture-Non-Binary-Voice/non-binary-voice-files"""
xml_file = os.path.join(root_path, "voice_over_recordings", meta_file) xml_file = os.path.join(root_path, "voice_over_recordings", meta_file)
@ -148,7 +148,7 @@ def sam_accenture(root_path, meta_file, **kwargs):
return items return items
def ruslan(root_path, meta_file, **kwargs): def ruslan(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalizes the RUSLAN meta data file to TTS format """Normalizes the RUSLAN meta data file to TTS format
https://ruslan-corpus.github.io/""" https://ruslan-corpus.github.io/"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
@ -163,7 +163,7 @@ def ruslan(root_path, meta_file, **kwargs):
return items return items
def css10(root_path, meta_file, **kwargs): def css10(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalizes the CSS10 dataset file to TTS format""" """Normalizes the CSS10 dataset file to TTS format"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
items = [] items = []
@ -177,7 +177,7 @@ def css10(root_path, meta_file, **kwargs):
return items return items
def nancy(root_path, meta_file, **kwargs): def nancy(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Normalizes the Nancy meta data file to TTS format""" """Normalizes the Nancy meta data file to TTS format"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
items = [] items = []
@ -240,7 +240,7 @@ def libri_tts(root_path, meta_files=None, ununsed_speakers=None):
return items return items
def custom_turkish(root_path, meta_file, **kwargs): def custom_turkish(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
items = [] items = []
speaker_name = "turkish-female" speaker_name = "turkish-female"
@ -298,7 +298,7 @@ def vctk(root_path, meta_files=None, wavs_path="wav48", ununsed_speakers=None):
return items return items
def vctk_slim(root_path, meta_files=None, wavs_path="wav48", ununsed_speakers=None): def vctk_slim(root_path, meta_files=None, wavs_path="wav48", ununsed_speakers=None): # pylint: disable=unused-argument
"""homepages.inf.ed.ac.uk/jyamagis/release/VCTK-Corpus.tar.gz""" """homepages.inf.ed.ac.uk/jyamagis/release/VCTK-Corpus.tar.gz"""
items = [] items = []
txt_files = glob(f"{os.path.join(root_path,'txt')}/**/*.txt", recursive=True) txt_files = glob(f"{os.path.join(root_path,'txt')}/**/*.txt", recursive=True)
@ -333,14 +333,14 @@ def mls(root_path, meta_files=None, ununsed_speakers=None):
# ======================================== VOX CELEB =========================================== # ======================================== VOX CELEB ===========================================
def voxceleb2(root_path, meta_file=None, **kwargs): def voxceleb2(root_path, meta_file=None, **kwargs): # pylint: disable=unused-argument
""" """
:param meta_file Used only for consistency with load_tts_samples api :param meta_file Used only for consistency with load_tts_samples api
""" """
return _voxcel_x(root_path, meta_file, voxcel_idx="2") return _voxcel_x(root_path, meta_file, voxcel_idx="2")
def voxceleb1(root_path, meta_file=None, **kwargs): def voxceleb1(root_path, meta_file=None, **kwargs): # pylint: disable=unused-argument
""" """
:param meta_file Used only for consistency with load_tts_samples api :param meta_file Used only for consistency with load_tts_samples api
""" """
@ -382,7 +382,7 @@ def _voxcel_x(root_path, meta_file, voxcel_idx):
return [x.strip().split("|") for x in f.readlines()] return [x.strip().split("|") for x in f.readlines()]
def baker(root_path: str, meta_file: str, **kwargs) -> List[List[str]]: def baker(root_path: str, meta_file: str, **kwargs) -> List[List[str]]: # pylint: disable=unused-argument
"""Normalizes the Baker meta data file to TTS format """Normalizes the Baker meta data file to TTS format
Args: Args:
@ -402,7 +402,7 @@ def baker(root_path: str, meta_file: str, **kwargs) -> List[List[str]]:
return items return items
def kokoro(root_path, meta_file, **kwargs): def kokoro(root_path, meta_file, **kwargs): # pylint: disable=unused-argument
"""Japanese single-speaker dataset from https://github.com/kaiidams/Kokoro-Speech-Dataset""" """Japanese single-speaker dataset from https://github.com/kaiidams/Kokoro-Speech-Dataset"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
items = [] items = []

2
TTS/tts/models/vits.py
View File

@ -644,7 +644,7 @@ class Vits(BaseTTS):
return self._log(ap, batch, outputs, "eval") return self._log(ap, batch, outputs, "eval")
@torch.no_grad() @torch.no_grad()
def test_run(self, ap, eval_loader=None) -> Tuple[Dict, Dict]: def test_run(self, ap) -> Tuple[Dict, Dict]:
"""Generic test run for `tts` models used by `Trainer`. """Generic test run for `tts` models used by `Trainer`.
You can override this for a different behaviour. You can override this for a different behaviour.

7
TTS/tts/utils/speakers.py
View File

@ -218,10 +218,11 @@ class SpeakerManager:
def get_random_speaker_aux_input(self) -> Dict: def get_random_speaker_aux_input(self) -> Dict:
if self.d_vectors: if self.d_vectors:
return {"speaker_id": None, "style_wav": None, "d_vector": self.d_vectors[random.choices(list(self.d_vectors.keys()))[0]]["embedding"]} return {"speaker_id": None, "style_wav": None, "d_vector": self.d_vectors[random.choices(list(self.d_vectors.keys()))[0]]["embedding"]}
elif self.speaker_ids:
if self.speaker_ids:
return {"speaker_id": self.speaker_ids[random.choices(list(self.speaker_ids.keys()))[0]], "style_wav": None, "d_vector": None} return {"speaker_id": self.speaker_ids[random.choices(list(self.speaker_ids.keys()))[0]], "style_wav": None, "d_vector": None}
else:
return {"speaker_id": None, "style_wav": None, "d_vector": None} return {"speaker_id": None, "style_wav": None, "d_vector": None}
def get_speakers(self) -> List: def get_speakers(self) -> List:
return self.speaker_ids return self.speaker_ids

2
requirements.txt
View File

@ -13,7 +13,7 @@ pyyaml
scipy>=0.19.0 scipy>=0.19.0
soundfile soundfile
tensorboardX tensorboardX
torch>=1.9.0 torch>=1.7
tqdm tqdm
numba==0.53 numba==0.53
umap-learn==0.5.1 umap-learn==0.5.1