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 2019-04-28 14:04:35 +02:00
parent 2e8446539f
commit 946098df94
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
config_cluster.json
View File

@ -1,6 +1,6 @@
{
"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",
"run_description": "Finetune 4702 orignal -> bn prenet - Mozilla with prenet bn, no mask, batch group size 0",
"audio":{
// Audio processing parameters
@ -41,7 +41,7 @@
"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": "bn", // ONLY TACOTRON2 - "original" or "bn".
"use_forward_attn": true, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster.
"use_forward_attn": false, // 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.
@ -56,11 +56,11 @@
"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.
"run_eval": false,
"test_delay_epochs": 5, //Until attention is aligned, testing only wastes computation time.
"run_eval": true,
"test_delay_epochs": 1, //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.
"meta_file_train": "metadata.txt", // DATASET-RELATED: metafile for training dataloader.
"meta_file_val": "metadata_val.txt", // DATASET-RELATED: metafile for evaluation dataloader.
"dataset": "mozilla", // 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": 150, // DATASET-RELATED: maximum text length