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 update

This commit is contained in:
Eren Golge 2019-04-23 14:58:00 +02:00
parent b0096728cb
commit 6df6f2c036
2 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.compute
View File

@ -1,11 +1,12 @@
#!/bin/bash
# ls ${USER_DIR}/MozillaDataset/Mozilla/batch1/wavs_no_processing
ls ${SHARED_DIR}/data/mozilla/Judy/
yes | apt-get install sox
soxi /data/rw/home/MozillaDataset/Mozilla/batch18/wavs_no_processing/18_167.wav
yes | apt-get install ffmpeg
soxi /data/ro/shared/data/mozilla/Judy/batch6/wavs_no_processing/6_126.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
# 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/
python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/mozilla/Judy/

10
config_cluster.json
View File

@ -1,6 +1,6 @@
{
"run_name": "mozilla-fattn",
"run_description": "Finetune 4583, Mozilla with 4 batch group size and fattn, batch size 16->24",
"run_name": "mozilla-nomask-fattn-bn",
"run_description": "Finetune 4700 orignal -> bn prenet - Mozilla with prenet bn, no mask, forward attn, batch group size 0",
"audio":{
// Audio processing parameters
@ -54,7 +54,7 @@
"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": 4, //Number of batches to shuffle after bucketing.
"batch_group_size": 0, //Number of batches to shuffle after bucketing.
"run_eval": false,
"test_delay_epochs": 5, //Until attention is aligned, testing only wastes computation time.
@ -65,8 +65,8 @@
"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": 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.
"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": "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