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 multiband melgan for mean-scale normalization and new audio parameters

This commit is contained in:
erogol 2020-06-22 14:56:12 +02:00
parent 2f3f43844e
commit 1324117703
2 changed files with 8 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
vocoder/configs/multiband_melgan_config.json
View File

@ -1,11 +1,10 @@
{ {
"run_name": "multiband-melgan", "run_name": "multiband-melgan",
"run_description": "multiband melgan", "run_description": "multiband melgan mean-var scaling",
// AUDIO PARAMETERS // AUDIO PARAMETERS
"audio":{ "audio":{
// stft parameters "fft_size": 1024, // number of stft frequency levels. Size of the linear spectogram frame.
"num_freq": 513, // number of stft frequency levels. Size of the linear spectogram frame.
"win_length": 1024, // stft window length in ms. "win_length": 1024, // stft window length in ms.
"hop_length": 256, // stft window hop-lengh 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_length_ms": null, // stft window length in ms.If null, 'win_length' is used.
@ -14,17 +13,17 @@
// Audio processing parameters // Audio processing parameters
"sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled. "sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
"preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. "preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
"ref_level_db": 20, // reference level db, theoretically 20db is the sound of air. "ref_level_db": 0, // reference level db, theoretically 20db is the sound of air.
// Silence trimming // Silence trimming
"do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) "do_trim_silence": true,// 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. "trim_db": 60, // threshold for timming silence. Set this according to your dataset.
// MelSpectrogram parameters // MelSpectrogram parameters
"num_mels": 80, // size of the mel spec frame. "num_mels": 80, // size of the mel spec frame.
"mel_fmin": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!! "mel_fmin": 50.0, // 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!! "mel_fmax": 7600.0, // maximum freq level for mel-spec. Tune for dataset!!
"spec_gain": 1.0, // scaler value appplied after log transform of spectrogram.
// Normalization parameters // Normalization parameters
"signal_norm": true, // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params. "signal_norm": true, // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params.
@ -32,7 +31,7 @@
"symmetric_norm": true, // move normalization to range [-1, 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] "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. "clip_norm": true, // clip normalized values into the range.
"stats_path": null // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored "stats_path": "/home/erogol/Data/LJSpeech-1.1/scale_stats.npy" // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
}, },
// DISTRIBUTED TRAINING // DISTRIBUTED TRAINING

2
vocoder/layers/losses.py
View File

@ -20,7 +20,7 @@ class TorchSTFT():
self.win_length, self.win_length,
self.window, self.window,
center=True, center=True,
pad_mode="constant", # compatible with audio.py pad_mode="reflect", # compatible with audio.py
normalized=False, normalized=False,
onesided=True) onesided=True)
M = o[:, :, :, 0] M = o[:, :, :, 0]