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

config update

This commit is contained in:
erogol 2020-09-24 12:37:58 +02:00
parent 4e93f90108
commit e0d4b88877
1 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
TTS/tts/configs/config.json
View File

@ -1,7 +1,7 @@
{ {
"model": "Tacotron2", "model": "Tacotron2",
"run_name": "ljspeech-ddc-bn", "run_name": "ljspeech-ddc",
"run_description": "tacotron2 with ddc and batch-normalization", "run_description": "tacotron2 with DDC and differential spectral loss.",
// AUDIO PARAMETERS // AUDIO PARAMETERS
"audio":{ "audio":{
@ -27,9 +27,9 @@
// 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": 20.0, "spec_gain": 1,
// 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.
@ -37,7 +37,7 @@
"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
}, },
// VOCABULARY PARAMETERS // VOCABULARY PARAMETERS
@ -90,7 +90,7 @@
// TACOTRON PRENET // TACOTRON PRENET
"memory_size": -1, // ONLY TACOTRON - size of the memory queue used fro storing last decoder predictions for auto-regression. If < 0, memory queue is disabled and decoder only uses the last prediction frame. "memory_size": -1, // ONLY TACOTRON - size of the memory queue used fro storing last decoder predictions for auto-regression. If < 0, memory queue is disabled and decoder only uses the last prediction frame.
"prenet_type": "bn", // "original" or "bn". "prenet_type": "original", // "original" or "bn".
"prenet_dropout": false, // enable/disable dropout at prenet. "prenet_dropout": false, // enable/disable dropout at prenet.
// TACOTRON ATTENTION // TACOTRON ATTENTION
@ -123,23 +123,23 @@
"enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars. "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
"num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values. "num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
"num_val_loader_workers": 4, // number of evaluation data loader processes. "num_val_loader_workers": 4, // number of evaluation data loader processes.
"batch_group_size": 0, //Number of batches to shuffle after bucketing. "batch_group_size": 4, //Number of batches to shuffle after bucketing.
"min_seq_len": 6, // DATASET-RELATED: minimum text length to use in training "min_seq_len": 6, // DATASET-RELATED: minimum text length to use in training
"max_seq_len": 153, // DATASET-RELATED: maximum text length "max_seq_len": 153, // DATASET-RELATED: maximum text length
// PATHS // PATHS
"output_path": "../../Mozilla-TTS/vctk-test/", "output_path": "/home/erogol/Models/LJSpeech/",
// PHONEMES // PHONEMES
"phoneme_cache_path": "../../Mozilla-TTS/vctk-test/", // phoneme computation is slow, therefore, it caches results in the given folder. "phoneme_cache_path": "/home/erogol/Models/phoneme_cache/", // phoneme computation is slow, therefore, it caches results in the given folder.
"use_phonemes": true, // use phonemes instead of raw characters. It is suggested for better pronounciation. "use_phonemes": true, // use phonemes instead of raw characters. It is suggested for better pronounciation.
"phoneme_language": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages "phoneme_language": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages
// MULTI-SPEAKER and GST // MULTI-SPEAKER and GST
"use_speaker_embedding": true, // use speaker embedding to enable multi-speaker learning. "use_speaker_embedding": false, // use speaker embedding to enable multi-speaker learning.
"use_gst": false, // use global style tokens
"use_external_speaker_embedding_file": false, // if true, forces the model to use external embedding per sample instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558 "use_external_speaker_embedding_file": false, // if true, forces the model to use external embedding per sample instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558
"external_speaker_embedding_file": "../../speakers-vctk-en.json", // if not null and use_external_speaker_embedding_file is true, it is used to load a specific embedding file and thus uses these embeddings instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558 "external_speaker_embedding_file": "../../speakers-vctk-en.json", // if not null and use_external_speaker_embedding_file is true, it is used to load a specific embedding file and thus uses these embeddings instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558
"use_gst": true, // use global style tokens
"gst": { // gst parameter if gst is enabled "gst": { // gst parameter if gst is enabled
"gst_style_input": null, // Condition the style input either on a "gst_style_input": null, // Condition the style input either on a
// -> wave file [path to wave] or // -> wave file [path to wave] or
@ -154,9 +154,9 @@
"datasets": // List of datasets. They all merged and they get different speaker_ids. "datasets": // List of datasets. They all merged and they get different speaker_ids.
[ [
{ {
"name": "vctk", "name": "ljspeech",
"path": "../../../datasets/VCTK-Corpus-removed-silence/", "path": "/home/erogol/Data/LJSpeech-1.1/",
"meta_file_train": ["p225", "p234", "p238", "p245", "p248", "p261", "p294", "p302", "p326", "p335", "p347"], // for vtck if list, ignore speakers id in list for train, its useful for test cloning with new speakers "meta_file_train": "metadata.csv", // for vtck if list, ignore speakers id in list for train, its useful for test cloning with new speakers
"meta_file_val": null "meta_file_val": null
} }
] ]