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

update speaker encoder config.json, for compatibility with the TTS model

This commit is contained in:
Edresson 2020-07-31 00:27:51 -03:00 committed by erogol
parent bc09ca8111
commit ac85ccae99
1 changed files with 27 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
mozilla_voice_tts/speaker_encoder/config.json
View File

@ -1,24 +1,30 @@
{
"run_name": "libritts_360-half",
"run_description": "train speaker encoder for libritts 360",
"audio": {
"run_name": "libritts_100+360-angleproto",
"run_description": "train speaker encoder for libritts 100 and 360",
"audio":{
// Audio processing parameters
"num_mels": 40, // size of the mel spec frame.
"num_freq": 1025, // number of stft frequency levels. Size of the linear spectogram frame.
"sample_rate": 16000, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
"frame_length_ms": 50, // stft window length in ms.
"frame_shift_ms": 12.5, // stft window hop-lengh in ms.
"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.
"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]
"signal_norm": true, // normalize the spec values in range [0, 1]
"symmetric_norm": true, // move normalization to range [-1, 1]
"max_norm": 4, // 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)
"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)
@ -34,10 +40,9 @@
"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": "/media/erogol/data_ssd/Models/libri_tts/speaker_encoder/", // DATASET-RELATED: output path for all training outputs.
"num_loader_workers": 0, // number of training data loader processes. Don't set it too big. 4-8 are good values.
"output_path": "../../checkpoints/libri_tts/speaker_encoder/", // DATASET-RELATED: output path for all training outputs.
"model": {
"input_dim": 40,
"input_dim": 80, // input_dim == num_mels
"proj_dim": 128,
"lstm_dim": 384,
"num_lstm_layers": 3
@ -46,13 +51,13 @@
[
{
"name": "libri_tts",
"path": "/home/erogol/Data/Libri-TTS/train-clean-360/",
"path": "../../datasets/LibriTTS/train-clean-360/",
"meta_file_train": null,
"meta_file_val": null
},
{
"name": "libri_tts",
"path": "/home/erogol/Data/Libri-TTS/train-clean-100/",
"path": "../../datasets/LibriTTS/train-clean-100/",
"meta_file_train": null,
"meta_file_val": null
}