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

config.json updated with more comments

pull/10/head
Eren Golge 2019-01-07 15:23:51 +01:00
parent c8d7a6a84e
commit 1dd8b134c6
1 changed files with 20 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
config.json
View File

@ -7,7 +7,7 @@
// Audio processing parameters
"num_mels": 80, // size of the mel spec frame.
"num_freq": 1025, // number of stft frequency levels. Size of the linear spectogram frame.
"sample_rate": 22050, // wav sample-rate. If different than the original data, it is resampled.
"sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
"frame_length_ms": 50, // stft window length in ms.
"frame_shift_ms": 12.5, // stft window hop-lengh in ms.
"preemphasis": 0.97, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
@ -25,30 +25,30 @@
"do_trim_silence": true // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
},
"embedding_size": 256,
"embedding_size": 256, // Character embedding vector length. You don't need to change it in general.
"text_cleaner": "english_cleaners",
"epochs": 1000,
"lr": 0.001,
"lr_decay": false,
"warmup_steps": 4000,
"epochs": 1000, // total number of epochs to train.
"lr": 0.001, // Initial learning rate. If Noam decay is active, maximum learning rate.
"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"
"batch_size": 20,
"eval_batch_size":32,
"r": 5,
"wd": 0.000001,
"checkpoint": true,
"save_step": 5000,
"print_step": 10,
"batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention.
"eval_batch_size":32,
"r": 5, // Number of frames to predict for step.
"wd": 0.000001, // Weight decay weight.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"save_step": 5000, // 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.
"run_eval": true,
"data_path": "../../Data/LJSpeech-1.1/", // can overwritten from command argument
"meta_file_train": "transcript_train.txt", // metafile for training dataloader.
"meta_file_val": "transcript_val.txt", // metafile for evaluation dataloader.
"dataset": "tweb", // 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, // minimum text length to use in training
"max_seq_len": 300, // maximum text length
"output_path": "/media/erogol/data_ssd/Data/models/tweb_models/", // output path for all training outputs.
"data_path": "../../Data/LJSpeech-1.1/", // DATASET-RELATED: can overwritten from command argument
"meta_file_train": "transcript_train.txt", // DATASET-RELATED: metafile for training dataloader.
"meta_file_val": "transcript_val.txt", // DATASET-RELATED: metafile for evaluation dataloader.
"dataset": "tweb", // 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": 300, // DATASET-RELATED: maximum text length
"output_path": "/media/erogol/data_ssd/Data/models/tweb_models/", // 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.
}