From c13e7f483a9f1c48770c94c4605bddfa21c3dcbd Mon Sep 17 00:00:00 2001 From: Eren Golge Date: Tue, 5 Nov 2019 17:06:33 +0100 Subject: [PATCH] commenting config.json --- config.json | 66 +++++++++++++++++++++++++++++++++++------------------ 1 file changed, 44 insertions(+), 22 deletions(-) diff --git a/config.json b/config.json index 623a599c..926f48bf 100644 --- a/config.json +++ b/config.json @@ -1,7 +1,9 @@ { + "model": "Tacotron2", // one of the model in models/ "run_name": "ljspeech-w/o-bd", "run_description": "tacotron2 without bidirectional decoder", + // AUDIO PARAMETERS "audio":{ // Audio processing parameters "num_mels": 80, // size of the mel spec frame. @@ -24,62 +26,82 @@ "do_trim_silence": true // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) }, + // DISTRIBUTED TRAINING "distributed":{ "backend": "nccl", "url": "tcp:\/\/localhost:54321" }, - "reinit_layers": [], + "reinit_layers": [], // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers. - "model": "Tacotron2", // one of the model in models/ + // TRAINING + "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, + "r": 7, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled. + "gradual_training": [[0, 7, 64], [1, 5, 64], [50000, 3, 32], [130000, 2, 16], [290000, 1, 8]], // ONLY TACOTRON - set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. + + // VALIDATION + "run_eval": true, + "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. + + // OPTIMIZER "grad_clip": 1, // upper limit for gradients for clipping. "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. + "wd": 0.000001, // Weight decay weight. "warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr" + + // TACOTRON PRENET "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. - "attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron. "prenet_type": "original", // "original" or "bn". "prenet_dropout": true, // enable/disable dropout at prenet. + + // ATTENTION + "attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron. "windowing": false, // Enables attention windowing. Used only in eval mode. "use_forward_attn": false, // if it uses forward attention. In general, it aligns faster. - "forward_attn_mask": false, + "forward_attn_mask": false, // Additional masking forcing monotonicity only in eval mode. "transition_agent": false, // enable/disable transition agent of forward attention. "location_attn": true, // enable_disable location sensitive attention. It is enabled for TACOTRON by default. "bidirectional_decoder": false, // use https://arxiv.org/abs/1907.09006. Use it, if attention does not work well with your dataset. "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. + + // STOPNET "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. + + // TENSORBOARD and LOGGING + "print_step": 25, // Number of steps to log traning on console. + "save_step": 10000, // Number of training steps expected to save traninpg stats and checkpoints. + "checkpoint": true, // If true, it saves checkpoints per "save_step" "tb_model_param_stats": false, // 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. It is overwritten by 'gradual_training'. - "eval_batch_size":16, - "r": 7, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled. - "gradual_training": [[0, 7, 64], [1, 5, 64], [50000, 3, 32], [130000, 2, 16], [290000, 1, 8]], // ONLY TACOTRON - set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. - "wd": 0.000001, // Weight decay weight. - "checkpoint": true, // If true, it saves checkpoints per "save_step" - "save_step": 10000, // Number of training steps expected to save traninpg stats and checkpoints. - "print_step": 25, // Number of steps to log traning on console. - "batch_group_size": 0, //Number of batches to shuffle after bucketing. - - "run_eval": true, - "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. - "min_seq_len": 6, // DATASET-RELATED: minimum text length to use in training - "max_seq_len": 150, // DATASET-RELATED: maximum text length - // "output_path": "../keep/", // DATASET-RELATED: output path for all training outputs. - "output_path": "/media/erogol/data_ssd/Models/runs/", + // DATA LOADING + "text_cleaner": "phoneme_cleaners", "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. + "batch_group_size": 0, //Number of batches to shuffle after bucketing. + "min_seq_len": 6, // DATASET-RELATED: minimum text length to use in training + "max_seq_len": 150, // DATASET-RELATED: maximum text length + + // PATHS + // "output_path": "../keep/", // DATASET-RELATED: output path for all training outputs. + "output_path": "/media/erogol/data_ssd/Models/runs/", + + // PHONEMES "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", + + // MULTI-SPEAKER and GST "use_speaker_embedding": false, // use speaker embedding to enable multi-speaker learning. "style_wav_for_test": null, // path to style wav file to be used in TacotronGST inference. "use_gst": false, // TACOTRON ONLY: use global style tokens + // DATASETS "datasets": // List of datasets. They all merged and they get different speaker_ids. [ {