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

nancy config changes

This commit is contained in:
Eren Golge 2019-03-12 01:26:21 +01:00
parent 3128378bdf
commit f7bfee0066
2 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.compute
View File

@ -1,7 +1,7 @@
#!/bin/bash
ls ${SHARED_DIR}/data/keithito
ls ${SHARED_DIR}/data/
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/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 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/Blizzard/Nancy/

12
config_cluster.json
View File

@ -1,6 +1,6 @@
{
"run_name": "bos",
"run_description": "bos character added to get away with the first char miss",
"run_name": "nancy-bn",
"run_description": "Nancy tacotron2 from scratch BN",
"audio":{
// Audio processing parameters
@ -51,15 +51,15 @@
"run_eval": true,
"test_delay_epochs": 100, //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": "metadata_train.csv", // DATASET-RELATED: metafile for training dataloader.
"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
"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": 1000, // 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": "ljspeech_us_phonemes", // phoneme computation is slow, therefore, it caches results in the given folder.
"phoneme_cache_path": "nancy_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"