fix broken imports in speaker encoder

checkpoints/libri_tts/speaker_encoder/libritts_100+360-angleproto-July-31-2020_12+37AM-debug/config.json

@@ -0,0 +1,60 @@
+
+"github_branch":"* dev-gst-embeddings",
+{
+    "run_name": "libritts_100+360-angleproto",
+    "run_description": "train speaker encoder for libritts 100 and 360",
+    "audio":{
+        // Audio processing parameters
+        "num_mels": 80,         // size of the mel spec frame. 
+        "num_freq": 1024,       // number of stft frequency levels. Size of the linear spectogram frame.
+        "sample_rate": 22050,   // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
+        "win_length": 1024,     // stft window length in ms.
+        "hop_length": 256,      // stft window hop-lengh in ms.
+        "frame_length_ms": null,  // stft window length in ms.If null, 'win_length' is used.
+        "frame_shift_ms": null,   // stft window hop-lengh in ms. If null, 'hop_length' is used.
+        "preemphasis": 0.98,    // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
+        "min_level_db": -100,   // normalization range
+        "ref_level_db": 20,     // reference level db, theoretically 20db is the sound of air.
+        "power": 1.5,           // value to sharpen wav signals after GL algorithm.
+        "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
+        // Normalization parameters
+        "signal_norm": true,    // normalize the spec values in range [0, 1]
+        "symmetric_norm": true, // move normalization to range [-1, 1]
+        "max_norm": 4.0,          // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
+        "clip_norm": true,      // clip normalized values into the range.
+        "mel_fmin": 0.0,         // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
+        "mel_fmax": 8000.0,        // maximum freq level for mel-spec. Tune for dataset!!
+        "do_trim_silence": false,  // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
+        "trim_db": 60          // threshold for timming silence. Set this according to your dataset.
+    },
+    "reinit_layers": [],
+    "loss": "angleproto", // "ge2e" to use Generalized End-to-End loss and "angleproto" to use Angular Prototypical loss (new SOTA)
+    "grad_clip": 3.0, // upper limit for gradients for clipping.
+    "epochs": 1000, // total number of epochs to train.
+    "lr": 0.0001, // Initial learning rate. If Noam decay is active, maximum learning rate.
+    "lr_decay": false, // if true, Noam learning rate decaying is applied through training.
+    "warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
+    "tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. 
+    "steps_plot_stats": 10, // number of steps to plot embeddings.
+    "num_speakers_in_batch": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
+    "wd": 0.000001, // Weight decay weight.
+    "checkpoint": true, // If true, it saves checkpoints per "save_step"
+    "save_step": 1000, // Number of training steps expected to save traning stats and checkpoints.
+    "print_step": 1, // Number of steps to log traning on console.
+    "output_path": "../../checkpoints/libri_tts/speaker_encoder/", // DATASET-RELATED: output path for all training outputs.
+    "model": {
+        "input_dim": 80, // input_dim == num_mels
+        "proj_dim": 128,
+        "lstm_dim": 384,
+        "num_lstm_layers": 3
+    },
+    "datasets": 
+        [
+            {
+                "name": "vctk",
+                "path": "../../../datasets/VCTK-Corpus-removed-silence/",
+                "meta_file_train": null,
+                "meta_file_val": null
+            }
+        ]
+}

checkpoints/libri_tts/speaker_encoder/libritts_100+360-angleproto-July-31-2020_12+38AM-debug/config.json

@@ -0,0 +1,60 @@
+
+"github_branch":"* dev-gst-embeddings",
+{
+    "run_name": "libritts_100+360-angleproto",
+    "run_description": "train speaker encoder for libritts 100 and 360",
+    "audio":{
+        // Audio processing parameters
+        "num_mels": 80,         // size of the mel spec frame. 
+        "num_freq": 1024,       // number of stft frequency levels. Size of the linear spectogram frame.
+        "sample_rate": 22050,   // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
+        "win_length": 1024,     // stft window length in ms.
+        "hop_length": 256,      // stft window hop-lengh in ms.
+        "frame_length_ms": null,  // stft window length in ms.If null, 'win_length' is used.
+        "frame_shift_ms": null,   // stft window hop-lengh in ms. If null, 'hop_length' is used.
+        "preemphasis": 0.98,    // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
+        "min_level_db": -100,   // normalization range
+        "ref_level_db": 20,     // reference level db, theoretically 20db is the sound of air.
+        "power": 1.5,           // value to sharpen wav signals after GL algorithm.
+        "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
+        // Normalization parameters
+        "signal_norm": true,    // normalize the spec values in range [0, 1]
+        "symmetric_norm": true, // move normalization to range [-1, 1]
+        "max_norm": 4.0,          // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
+        "clip_norm": true,      // clip normalized values into the range.
+        "mel_fmin": 0.0,         // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
+        "mel_fmax": 8000.0,        // maximum freq level for mel-spec. Tune for dataset!!
+        "do_trim_silence": false,  // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
+        "trim_db": 60          // threshold for timming silence. Set this according to your dataset.
+    },
+    "reinit_layers": [],
+    "loss": "angleproto", // "ge2e" to use Generalized End-to-End loss and "angleproto" to use Angular Prototypical loss (new SOTA)
+    "grad_clip": 3.0, // upper limit for gradients for clipping.
+    "epochs": 1000, // total number of epochs to train.
+    "lr": 0.0001, // Initial learning rate. If Noam decay is active, maximum learning rate.
+    "lr_decay": false, // if true, Noam learning rate decaying is applied through training.
+    "warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
+    "tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. 
+    "steps_plot_stats": 10, // number of steps to plot embeddings.
+    "num_speakers_in_batch": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
+    "wd": 0.000001, // Weight decay weight.
+    "checkpoint": true, // If true, it saves checkpoints per "save_step"
+    "save_step": 1000, // Number of training steps expected to save traning stats and checkpoints.
+    "print_step": 1, // Number of steps to log traning on console.
+    "output_path": "../../checkpoints/libri_tts/speaker_encoder/", // DATASET-RELATED: output path for all training outputs.
+    "model": {
+        "input_dim": 80, // input_dim == num_mels
+        "proj_dim": 128,
+        "lstm_dim": 384,
+        "num_lstm_layers": 3
+    },
+    "datasets": 
+        [
+            {
+                "name": "vctk",
+                "path": "../../../datasets/VCTK-Corpus-removed-silence/",
+                "meta_file_train": null,
+                "meta_file_val": null
+            }
+        ]
+}

mozilla_voice_tts/bin/train_encoder.py

@@ -13,7 +13,7 @@ from torch.utils.data import DataLoader
 from mozilla_voice_tts.generic_utils import count_parameters
 from mozilla_voice_tts.speaker_encoder.dataset import MyDataset
 from mozilla_voice_tts.speaker_encoder.generic_utils import save_best_model
-from mozilla_voice_tts.speaker_encoder.loss import GE2ELoss
+from mozilla_voice_tts.speaker_encoder.losses import GE2ELoss
 from mozilla_voice_tts.speaker_encoder.model import SpeakerEncoder
 from mozilla_voice_tts.speaker_encoder.visual import plot_embeddings
 from mozilla_voice_tts.tts.datasets.preprocess import load_meta_data

mozilla_voice_tts/speaker_encoder/config.json

@@ -50,14 +50,8 @@
     "datasets": 
         [
             {
-                "name": "libri_tts",
+                "name": "vctk",
-                "path": "../../datasets/LibriTTS/train-clean-360/",
+                "path": "../../../datasets/VCTK-Corpus-removed-silence/",
-                "meta_file_train": null,
-                "meta_file_val": null
-            },
-            {
-                "name": "libri_tts",
-                "path": "../../datasets/LibriTTS/train-clean-100/",
                 "meta_file_train": null,
                 "meta_file_val": null
             }