diff --git a/config.json b/config.json index 38ca74e1..3c66beb4 100644 --- a/config.json +++ b/config.json @@ -1,12 +1,12 @@ { - "run_name": "ljspeech", - "run_description": "finetune 4241 for align with architectural changes", + "run_name": "mozilla-no-loc", + "run_description": "using Bahdenau attention, with original prenet.", "audio":{ // 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": 0.98, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. @@ -29,46 +29,49 @@ "url": "tcp:\/\/localhost:54321" }, - "reinit_layers": [], //set which layers to be reinitialized in finetunning. Only used if --restore_model is provided. + "reinit_layers": [], - "model": "Tacotron2", // one of the model in models/ - "grad_clip": 1, // upper limit for gradients for clipping. - "epochs": 1000, // total number of epochs to train. - "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. - "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. + "model": "Tacotron2", // one of the model in models/ + "grad_clip": 1, // upper limit for gradients for clipping. + "epochs": 1000, // total number of epochs to train. + "lr": 0.0002, // 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" + "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": "bn", // ONLY TACOTRON2 - "original" or "bn". - "use_forward_attn": true, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster. - "transition_agent": true, // ONLY TACOTRON2 - enable/disable transition agent of forward attention. - "loss_masking": false, // enable / disable loss masking against the sequence padding. + "prenet_type": "original", // ONLY TACOTRON2 - "original" or "bn". + "prenet_dropout": true, // ONLY TACOTRON2 - enable/disable dropout at prenet. + "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. + "location_attn": false, // ONLY TACOTRON2 - enable_disable location sensitive attention. It is enabled for TACOTRON by default. + "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. + "stopnet": false, // Train stopnet predicting the end of synthesis. + "separate_stopnet": false, // 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. - - "batch_size": 16, // 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. "eval_batch_size":16, "r": 1, // 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": 1000, // Number of training steps expected to save traning stats and checkpoints. - "print_step": 100, // Number of steps to log traning on console. + "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. - "batch_group_size": 8, // Number of batches to shuffle after bucketing. + "batch_group_size": 0, //Number of batches to shuffle after bucketing. "run_eval": true, - "test_delay_epochs": 2, //Until attention is aligned, testing only wastes computation time. - "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 + "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": "metadata_train.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 - "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. + "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_val_loader_workers": 4, // number of evaluation data loader processes. - "phoneme_cache_path": "ljspeech_phonemes", // phoneme computation is slow, therefore, it caches results in the given folder. + "phoneme_cache_path": "mozilla_us_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" diff --git a/config_cluster.json b/config_cluster.json index b04c4df1..4baebb60 100644 --- a/config_cluster.json +++ b/config_cluster.json @@ -48,7 +48,7 @@ "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. "stopnet": false, // Train stopnet predicting the end of synthesis. - "separate_stopnet": false, // train stopnet seperately. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER. + "separate_stopnet": false, // 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. "batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. "eval_batch_size":16,