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 fixes and enable graves attention wq

This commit is contained in:
erogol 2020-02-07 13:00:04 +01:00
parent 9809fda144
commit 2996d63145
1 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
config.json
View File

@ -23,8 +23,8 @@
"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": 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.
"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.
},
// DISTRIBUTED TRAINING
@ -62,14 +62,14 @@
"prenet_dropout": true, // enable/disable dropout at prenet.
// ATTENTION
"attention_type": "original", // 'original' or 'graves'
"attention_heads": 5, // number of attention heads (only for 'graves')
"attention_type": "graves", // 'original' or 'graves'
"attention_heads": 4, // number of attention heads (only for 'graves')
"attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron.
"windowing": false, // Enables attention windowing. Used only in eval mode.
"use_forward_attn": false, // if it uses forward attention. In general, it aligns faster.
"forward_attn_mask": false, // Additional masking forcing monotonicity only in eval mode.
"transition_agent": false, // enable/disable transition agent of forward attention.
"location_attn": true, // enable_disable location sensitive attention. It is enabled for TACOTRON by default.
"location_attn": false, // enable_disable location sensitive attention. It is enabled for TACOTRON by default.
"bidirectional_decoder": false, // use https://arxiv.org/abs/1907.09006. Use it, if attention does not work well with your dataset.
// STOPNET
@ -92,8 +92,8 @@
"max_seq_len": 150, // DATASET-RELATED: maximum text length
// PATHS
"output_path": "/data5/rw/pit/keep/", // DATASET-RELATED: output path for all training outputs.
// "output_path": "/media/erogol/data_ssd/Models/runs/",
// "output_path": "/data5/rw/pit/keep/", // DATASET-RELATED: output path for all training outputs.
"output_path": "/home/erogol/Models/LJSpeech/",
// PHONEMES
"phoneme_cache_path": "mozilla_us_phonemes", // phoneme computation is slow, therefore, it caches results in the given folder.
@ -110,10 +110,10 @@
[
{
"name": "ljspeech",
"path": "/root/LJSpeech-1.1/",
"path": "/home/erogol/Data/LJSpeech-1.1/",
// "path": "/home/erogol/Data/LJSpeech-1.1",
"meta_file_train": "metadata_train.csv",
"meta_file_val": "metadata_val.csv"
"meta_file_train": "metadata.csv",
"meta_file_val": null
}
]