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 updates for cluster

This commit is contained in:
Eren Golge 2019-03-12 10:43:53 +01:00
parent e546efbed7
commit 47037ea834
3 changed files with 11 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.compute
View File

@ -4,4 +4,4 @@ pip3 install https://download.pytorch.org/whl/cu100/torch-1.0.1.post2-cp36-cp36m
yes | apt-get install espeak yes | apt-get install espeak
python3 setup.py develop python3 setup.py develop
# python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ --restore_path ${USER_DIR}/best_model.pth.tar # python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ --restore_path ${USER_DIR}/best_model.pth.tar
python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ python3 train.py --config_path config.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/

2
config.json
View File

@ -42,7 +42,7 @@
"batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. "batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention.
"eval_batch_size":32, "eval_batch_size":32,
"r": 5, // Number of frames to predict for step. "r": 5, // Number of frames to predict for step.
"wd": 0.00001, // Weight decay weight. "wd": 0.000001, // Weight decay weight.
"checkpoint": true, // If true, it saves checkpoints per "save_step" "checkpoint": true, // If true, it saves checkpoints per "save_step"
"save_step": 5000, // Number of training steps expected to save traning stats and checkpoints. "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. "print_step": 50, // Number of steps to log traning on console.

13
config_cluster.json
View File

@ -1,6 +1,6 @@
{ {
"model_name": "tts-master", "model_name": "tts-master",
"model_description": "tts master cluster test", "model_description": "tts master with symbols update",
"audio":{ "audio":{
"audio_processor": "audio", // to use dictate different audio processors, if available. "audio_processor": "audio", // to use dictate different audio processors, if available.
@ -25,6 +25,11 @@
"do_trim_silence": true // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) "do_trim_silence": true // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
}, },
"distributed":{
"backend": "nccl",
"url": "tcp:\/\/localhost:54321"
},
"embedding_size": 256, // Character embedding vector length. You don't need to change it in general. "embedding_size": 256, // Character embedding vector length. You don't need to change it in general.
"text_cleaner": "phoneme_cleaners", "text_cleaner": "phoneme_cleaners",
"epochs": 1000, // total number of epochs to train. "epochs": 1000, // total number of epochs to train.
@ -46,9 +51,9 @@
"run_eval": true, "run_eval": true,
"data_path": "/media/erogol/data_ssd/Data/LJSpeech-1.1", // DATASET-RELATED: can overwritten from command argument "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_train": "metadata_train.csv", // DATASET-RELATED: metafile for training dataloader.
"meta_file_val": "prompts_val.data", // DATASET-RELATED: metafile for evaluation dataloader. "meta_file_val": "metadata_val.csv", // 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 "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 "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": 300, // DATASET-RELATED: maximum text length
"output_path": "models/", // DATASET-RELATED: output path for all training outputs. "output_path": "models/", // DATASET-RELATED: output path for all training outputs.