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 2019-07-21 16:32:56 +02:00
parent d47ba5d310
commit 721e781216
1 changed files with 20 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
config.json
View File

@ -1,6 +1,6 @@
{ {
"run_name": "mozilla-no-loc-fattn-stopnet-sigmoid-loss_masking", "run_name": "ljspeech",
"run_description": "using forward attention, with original prenet, loss masking,separate stopnet, sigmoid. Compare this with 4817. Pytorch DPP", "run_description": "gradual training with prenet frame size 1. Comparing to memory queue in gradual training. ",
"audio":{ "audio":{
// Audio processing parameters // Audio processing parameters
@ -31,43 +31,45 @@
"reinit_layers": [], "reinit_layers": [],
"model": "Tacotron2", // one of the model in models/ "model": "Tacotron", // one of the model in models/
"grad_clip": 1, // upper limit for gradients for clipping. "grad_clip": 1, // upper limit for gradients for clipping.
"epochs": 1000, // total number of epochs to train. "epochs": 1000, // total number of epochs to train.
"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": -1, // ONLY TACOTRON - size of the memory queue used fro storing last decoder predictions for auto-regression. If < 0, memory queue is disabled and decoder only uses the last prediction frame.
"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,
"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": 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. It is overwritten by 'gradual_training'.
"eval_batch_size":16, "eval_batch_size":16,
"r": 1, // Number of frames to predict for step. "r": 7, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
"gradual_training": [[0, 7, 32], [10000, 5, 32], [50000, 3, 32], [130000, 2, 16], [290000, 1, 8]], // set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled.
"wd": 0.000001, // 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": 1000, // Number of training steps expected to save traning stats and checkpoints. "save_step": 10000, // Number of training steps expected to save traning stats and checkpoints.
"print_step": 10, // Number of steps to log traning on console. "print_step": 25, // 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": true, "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": "/media/erogol/data_ssd/Data/Mozilla/", // DATASET-RELATED: can overwritten from command argument "data_path": "/home/erogol/Data/LJSpeech-1.1/", // DATASET-RELATED: can overwritten from command argument
"meta_file_train": "metadata_train.txt", // DATASET-RELATED: metafile for training dataloader. "meta_file_train": "metadata_train.csv", // DATASET-RELATED: metafile for training dataloader.
"meta_file_val": "metadata_val.txt", // DATASET-RELATED: metafile for evaluation dataloader. "meta_file_val": "metadata_val.csv", // 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 "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": 6, // DATASET-RELATED: minimum text length to use in training
"max_seq_len": 150, // DATASET-RELATED: maximum text length "max_seq_len": 150, // DATASET-RELATED: maximum text length
"output_path": "../keep/", // DATASET-RELATED: output path for all training outputs. "output_path": "../keep/", // DATASET-RELATED: output path for all training outputs.
"num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values. "num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
@ -76,6 +78,6 @@
"use_phonemes": true, // use phonemes instead of raw characters. It is suggested for better pronounciation. "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 "phoneme_language": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages
"text_cleaner": "phoneme_cleaners", "text_cleaner": "phoneme_cleaners",
"use_speaker_embedding": false // whether to use additional embeddings for separate speakers "use_speaker_embedding": false
} }