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 upate

This commit is contained in:
Eren Golge 2019-04-18 17:34:54 +02:00
parent 8b1da591fc
commit 9915220539
2 changed files with 16 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
.compute
View File

@ -1,7 +1,11 @@
#!/bin/bash
ls ${SHARED_DIR}/data/
# ls ${USER_DIR}/MozillaDataset/Mozilla/batch1/wavs_no_processing
yes | apt-get install sox
soxi /data/rw/home/MozillaDataset/Mozilla/batch18/wavs_no_processing/18_167.wav
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 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/ --restore_path ${USER_DIR}/best_model_4467.pth.tar
python3 distribute.py --config_path config_cluster.json --data_path ${USER_DIR}/Mozilla/
# wget https://www.dropbox.com/s/evaouukiwb7krz8/MozillaDataset.tar.gz?dl=0 -O ${USER_DIR}/MozillaDataset.tar.gz
# tar -xzvf ${USER_DIR}/MozillaDataset.tar.gz --no-same-owner -C ${USER_DIR}
# python3 distribute.py --config_path config_cluster.json --data_path ${USER_DIR}/MozillaDataset/Mozilla/ --restore_path ${USER_DIR}/best_model_4583.pth.tar
python3 distribute.py --config_path config_cluster.json --data_path ${USER_DIR}/MozillaDataset/Mozilla/

18
config_cluster.json
View File

@ -1,6 +1,6 @@
{
"run_name": "mozilla-fattn",
"run_description": "Finetune 4583, Mozilla with 0 batch group size and fattn",
"run_description": "Finetune 4583, Mozilla with 4 batch group size and fattn, batch size 16->24",
"audio":{
// Audio processing parameters
@ -40,13 +40,13 @@
"windowing": false, // Enables attention windowing. Used only in eval mode.
"memory_size": 5, // ONLY TACOTRON - memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5.
"attention_norm": "softmax", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron.
"prenet_type": "original", // ONLY TACOTRON2 - "original" or "bn".
"prenet_type": "bn", // ONLY TACOTRON2 - "original" or "bn".
"use_forward_attn": true, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster.
"transition_agent": false, // ONLY TACOTRON2 - enable/disable transition agent of forward attention.
"loss_masking": false, // enable / disable loss masking against the sequence padding.
"enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
"batch_size": 16, // Batch size for training. Lower values than 32 might cause hard to learn attention.
"batch_size": 2, // 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": 0.000001, // Weight decay weight.
@ -54,10 +54,10 @@
"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": true, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
"batch_group_size": 0, //Number of batches to shuffle after bucketing.
"batch_group_size": 4, //Number of batches to shuffle after bucketing.
"run_eval": false,
"test_delay_epochs": 10, //Until attention is aligned, testing only wastes computation time.
"test_delay_epochs": 5, //Until attention is aligned, testing only wastes computation time.
"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.
@ -65,10 +65,10 @@
"min_seq_len": 0, // DATASET-RELATED: minimum text length to use in training
"max_seq_len": 150, // DATASET-RELATED: maximum text length
"output_path": "../keep/", // 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": "nancy_us_phonemes", // phoneme computation is slow, therefore, it caches results in the given folder.
"num_loader_workers": 0, // number of training data loader processes. Don't set it too big. 4-8 are good values.
"num_val_loader_workers": 0, // number of evaluation data loader processes.
"phoneme_cache_path": "mozilla_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
"text_cleaner": "phoneme_cleaners"
}
}