wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-13 12:20:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Mass refactoring

Browse Source
This commit is contained in:
erogol
2020-07-17 11:16:05 +02:00
parent 3bc38517aa
commit 82dd465365
148 changed files with 3698 additions and 13887 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/inputs/test_vocoder_audio_config.json
+24
View File
@@ -0,0 +1,24 @@
{
"audio":{
"num_mels": 80, // size of the mel spec frame.
"num_freq": 513, // number of stft frequency levels. Size of the linear spectogram frame.
"sample_rate": 22050, // wav sample-rate. If different than the original data, it is resampled.
"frame_length_ms": null, // stft window length in ms.
"frame_shift_ms": null, // stft window hop-lengh in ms.
"hop_length": 256,
"win_length": 1024,
"preemphasis": 0.97, // 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": 30,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
"signal_norm": true, // normalize the spec values in range [0, 1]
"symmetric_norm": true, // move normalization to range [-1, 1]
"clip_norm": true, // clip normalized values into the range.
"max_norm": 4, // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
"mel_fmin": 0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
"mel_fmax": 8000, // maximum freq level for mel-spec. Tune for dataset!!
"do_trim_silence": false
}
}