From 303dc9d62e9820147554ce7965c3b7df98d2fe91 Mon Sep 17 00:00:00 2001 From: Eren Golge Date: Mon, 8 Apr 2019 16:45:50 +0200 Subject: [PATCH] config update for ljspeech --- config.json | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/config.json b/config.json index c6cc5d05..3e054e72 100644 --- a/config.json +++ b/config.json @@ -1,6 +1,6 @@ { - "run_name": "bos", - "run_description": "finetune entropy model due to some spelling mistakes.", + "run_name": "ljspeech", + "run_description": "finetune 4241 for align with architectural changes", "audio":{ // Audio processing parameters @@ -40,10 +40,10 @@ "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. "attention_norm": "softmax", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron. - "prenet_type": "original", // ONLY TACOTRON2 - "original" or "bn". + "prenet_type": "bn", // ONLY TACOTRON2 - "original" or "bn". "use_forward_attn": false, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster. - "batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. + "batch_size": 16, // Batch size for training. Lower values than 32 might cause hard to learn attention. "eval_batch_size":16, "r": 1, // Number of frames to predict for step. "wd": 0.000001, // Weight decay weight. @@ -55,16 +55,16 @@ "run_eval": true, "test_delay_epochs": 2, //Until attention is aligned, testing only wastes computation time. - "data_path": "/media/erogol/data_ssd/Data/Nancy/", // 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. - "dataset": "nancy", // DATASET-RELATED: one of TTS.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py + "data_path": "/home/erogol/Data/LJSpeech-1.1", // DATASET-RELATED: can overwritten from command argument + "meta_file_train": "metadata_train.csv", // DATASET-RELATED: metafile for training dataloader. + "meta_file_val": "metadata_val.csv", // DATASET-RELATED: metafile for evaluation dataloader. + "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 "max_seq_len": 150, // DATASET-RELATED: maximum text length "output_path": "/media/erogol/data_ssd/Data/models/ljspeech_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. - "phoneme_cache_path": "nancy_us_phonemes2", // phoneme computation is slow, therefore, it caches results in the given folder. + "phoneme_cache_path": "ljspeech_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 "text_cleaner": "phoneme_cleaners"