coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

libri tts config, and bug fix

pull/10/head
Eren Golge 2019-07-16 15:17:38 +02:00
parent a953961535
commit aec7f02817
2 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
config_libritts.json
View File

@ -37,22 +37,22 @@
"lr": 0.0001, // Initial learning rate. If Noam decay is active, maximum learning rate. "lr": 0.0001, // Initial learning rate. If Noam decay is active, maximum learning rate.
"lr_decay": false, // if true, Noam learning rate decaying is applied through training. "lr_decay": false, // if true, Noam learning rate decaying is applied through training.
"warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr" "warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
"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. "memory_size": 5, // ONLY TACOTRON - memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5.
"attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron. "attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron.
"prenet_type": "original", // ONLY TACOTRON2 - "original" or "bn". "prenet_type": "original", // ONLY TACOTRON2 - "original" or "bn".
"prenet_dropout": true, // ONLY TACOTRON2 - enable/disable dropout at prenet. "prenet_dropout": true, // ONLY TACOTRON2 - enable/disable dropout at prenet.
"use_forward_attn": true, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster. "windowing": false, // Enables attention windowing. Used only in eval mode.
"use_forward_attn": false, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster.
"forward_attn_mask": false, "forward_attn_mask": false,
"transition_agent": false, // ONLY TACOTRON2 - enable/disable transition agent of forward attention. "transition_agent": false, // ONLY TACOTRON2 - enable/disable transition agent of forward attention.
"location_attn": false, // ONLY TACOTRON2 - enable_disable location sensitive attention. It is enabled for TACOTRON by default. "location_attn": true, // ONLY TACOTRON2 - enable_disable location sensitive attention. It is enabled for TACOTRON by default.
"loss_masking": true, // enable / disable loss masking against the sequence padding. "loss_masking": true, // enable / disable loss masking against the sequence padding.
"enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars. "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
"stopnet": true, // Train stopnet predicting the end of synthesis. "stopnet": true, // Train stopnet predicting the end of synthesis.
"separate_stopnet": true, // Train stopnet seperately if 'stopnet==true'. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER. "separate_stopnet": true, // Train stopnet seperately if 'stopnet==true'. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER.
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. "tb_model_param_stats": true, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
"batch_size": 16, // Batch size for training. Lower values than 32 might cause hard to learn attention. "batch_size": 24, // Batch size for training. Lower values than 32 might cause hard to learn attention.
"eval_batch_size":16, "eval_batch_size":16,
"r": 1, // Number of frames to predict for step. "r": 1, // Number of frames to predict for step.
"wd": 0.000001, // Weight decay weight. "wd": 0.000001, // Weight decay weight.
@ -61,7 +61,7 @@
"print_step": 10, // Number of steps to log traning on console. "print_step": 10, // Number of steps to log traning on console.
"batch_group_size": 0, //Number of batches to shuffle after bucketing. "batch_group_size": 0, //Number of batches to shuffle after bucketing.
"run_eval": false, "run_eval": true,
"test_delay_epochs": 5, //Until attention is aligned, testing only wastes computation time. "test_delay_epochs": 5, //Until attention is aligned, testing only wastes computation time.
"test_sentences_file": null, // set a file to load sentences to be used for testing. If it is null then we use default english sentences. "test_sentences_file": null, // set a file to load sentences to be used for testing. If it is null then we use default english sentences.
"data_path": "/home/erogol/Data/Libri-TTS/train-clean-360/", // DATASET-RELATED: can overwritten from command argument "data_path": "/home/erogol/Data/Libri-TTS/train-clean-360/", // DATASET-RELATED: can overwritten from command argument

2
utils/generic_utils.py
View File

@ -275,7 +275,7 @@ def setup_model(num_chars, num_speakers, c):
elif c.model.lower() == "tacotron2": elif c.model.lower() == "tacotron2":
model = MyModel( model = MyModel(
num_chars=num_chars, num_chars=num_chars,
num_speakers=c.num_speakers, num_speakers=num_speakers,
r=c.r, r=c.r,
attn_win=c.windowing, attn_win=c.windowing,
attn_norm=c.attention_norm, attn_norm=c.attention_norm,