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

.compute update

This commit is contained in:
Eren Golge 2019-02-20 16:45:31 +01:00
parent e825944100
commit 6e86d0d0c4
2 changed files with 64 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.compute
View File

@ -1,5 +1,5 @@
#!/bin/bash
source ../tmp/venv/bin/activate
# python extract_features.py --data_path ${DATA_ROOT}/shared/data/keithito/LJSpeech-1.1/ --cache_path ~/tts_cache/ --config config.json --num_proc 12 --dataset ljspeech --meta_file metadata.csv --val_split 1000 --process_audio true
# python train.py --config_path config.json --data_path ~/tts_cache/ --debug true
python train.py --config_path config.json --data_path ${DATA_ROOT}/shared/data/Blizzard/Nancy/ --debug true
pip3 install https://download.pytorch.org/whl/cu100/torch-1.0.1.post2-cp36-cp36m-linux_x86_64.whl
yes | apt-get install espeak
python3 setup.py develop
python3 train.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/ --debug true

60
config_cluster.json Normal file
View File

@ -0,0 +1,60 @@
{
"model_name": "tts-master",
"model_description": "tts master cluster test",
"audio":{
"audio_processor": "audio", // to use dictate different audio processors, if available.
// Audio processing parameters
"num_mels": 80, // size of the mel spec frame.
"num_freq": 1025, // 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": 50, // stft window length in ms.
"frame_shift_ms": 12.5, // stft window hop-lengh in ms.
"preemphasis": 0.98, // 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": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
// Normalization parameters
"signal_norm": true, // normalize the spec values in range [0, 1]
"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)
},
"embedding_size": 256, // Character embedding vector length. You don't need to change it in general.
"text_cleaner": "phoneme_cleaners",
"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.
"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.
"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.
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
"run_eval": true,
"data_path": "/media/erogol/data_ssd/Data/LJSpeech-1.1", // DATASET-RELATED: can overwritten from command argument
"meta_file_train": "prompts_train.data", // DATASET-RELATED: metafile for training dataloader.
"meta_file_val": "prompts_val.data", // DATASET-RELATED: metafile for evaluation dataloader.
"dataset": "nancy", // 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
"output_path": "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": "phonemes_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.
"phoneme_language": "en-us" // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages
}