From 57cbb3ab0c3792e055d55b1de47a9145ad793ba7 Mon Sep 17 00:00:00 2001 From: erogol Date: Mon, 9 Mar 2020 21:02:44 +0100 Subject: [PATCH] config update for guided attention and normalization --- config.json | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/config.json b/config.json index a113836f..96b6576a 100644 --- a/config.json +++ b/config.json @@ -7,11 +7,11 @@ "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. + "num_freq": 513, // number of stft frequency levels. Size of the linear spectogram frame. "sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled. "win_length": 1024, // stft window length in ms. "hop_length": 256, // 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. + "preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. "min_level_db": -100, // normalization range "ref_level_db": 20, // reference level db, theoretically 20db is the sound of air. "power": 1.5, // value to sharpen wav signals after GL algorithm. @@ -19,7 +19,7 @@ // Normalization parameters "signal_norm": true, // normalize the spec values in range [0, 1] "symmetric_norm": true, // move normalization to range [-1, 1] - "max_norm": 4.0, // scale normalization to range [-max_norm, max_norm] or [0, max_norm] + "max_norm": 1.0, // scale normalization to range [-max_norm, max_norm] or [0, max_norm] "clip_norm": true, // clip normalized values into the range. "mel_fmin": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!! "mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!! @@ -41,6 +41,7 @@ "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, 32], [290000, 1, 32]], //set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. For Tacotron, you might need to reduce the 'batch_size' as you proceeed. "loss_masking": true, // enable / disable loss masking against the sequence padding. + "ga_alpha": 10.0, // weight for guided attention loss. If > 0, guided attention is enabled. // VALIDATION "run_eval": true, @@ -69,7 +70,7 @@ "use_forward_attn": false, // if it uses forward attention. In general, it aligns faster. "forward_attn_mask": false, // Additional masking forcing monotonicity only in eval mode. "transition_agent": false, // enable/disable transition agent of forward attention. - "location_attn": false, // enable_disable location sensitive attention. It is enabled for TACOTRON by default. + "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. // STOPNET @@ -89,13 +90,13 @@ "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 + "max_seq_len": 153, // DATASET-RELATED: maximum text length // PATHS "output_path": "/home/erogol/Models/", // PHONEMES - "phoneme_cache_path": "mozilla_us_phonemes_2_1", // phoneme computation is slow, therefore, it caches results in the given folder. + "phoneme_cache_path": "mozilla_us_phonemes_3", // 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