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.json update to set model architecture and tacotron2 training parameters

This commit is contained in:
Eren Golge 2019-03-06 13:09:21 +01:00
parent 5133db82ad
commit 007bef5c35
1 changed files with 18 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
config.json
View File

@ -1,6 +1,6 @@
{
"model_name": "queue",
"model_description": "Queue memory and change lower r incrementatlly",
"run_name": "queue",
"run_description": "Queue memory and change lower r incrementatlly",
"audio":{
// Audio processing parameters
@ -19,9 +19,9 @@
"symmetric_norm": false, // move normalization to range [-1, 1]
"max_norm": 1, // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
"clip_norm": true, // clip normalized values into the range.
"mel_fmin": null, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
"mel_fmax": null, // 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)
"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)
},
"distributed":{
@ -29,22 +29,23 @@
"url": "tcp:\/\/localhost:54321"
},
"text_cleaner": "phoneme_cleaners",
"model": "Tacotron", // one of the model in models/
"grad_clip": 0.02, // upper limit for gradients for clipping.
"epochs": 1000, // total number of epochs to train.
"lr": 0.0001, // Initial learning rate. If Noam decay is active, maximum learning rate.
"lr_decay": false, // if true, Noam learning rate decaying is applied through training.
"loss_weight": 0.0, // loss weight to emphasize lower frequencies. Lower frequencies are in general more important for speech signals.
"warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
"windowing": false, // Enables attention windowing. Used only in eval mode.
"memory_size": 5, // memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5.
"memory_size": 5, // TO BE IMPLEMENTED -- memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5.
"batch_group_size": 3,
"batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention.
"eval_batch_size":32,
"r": 5, // Number of frames to predict for step.
"wd": 0.00001, // Weight decay weight.
"batch_size": 16, // Batch size for training. Lower values than 32 might cause hard to learn attention.
"eval_batch_size":16,
"r": 1, // Number of frames to predict for step.
"wd": 0.000005, // Weight decay weight.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"save_step": 5000, // Number of training steps expected to save traning stats and checkpoints.
"print_step": 50, // Number of steps to log traning on console.
"save_step": 1000, // Number of training steps expected to save traning stats and checkpoints.
"print_step": 10, // Number of steps to log traning on console.
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
"batch_group_size": 8, //Number of batches to shuffle after bucketing.
@ -55,11 +56,12 @@
"meta_file_val": "metadata_val.csv", // DATASET-RELATED: metafile for evaluation dataloader.
"dataset": "ljspeech", // DATASET-RELATED: one of TTS.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py
"min_seq_len": 0, // DATASET-RELATED: minimum text length to use in training
"max_seq_len": 300, // DATASET-RELATED: maximum text length
"max_seq_len": 1000, // DATASET-RELATED: maximum text length
"output_path": "/media/erogol/data_ssd/Data/models/ljspeech_models/", // DATASET-RELATED: output path for all training outputs.
"num_loader_workers": 8, // 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.
"phoneme_cache_path": "ljspeech_us_phonemes", // 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.
"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
"text_cleaner": "phoneme_cleaners"
}