From 84c5c4a5871ffe3f87e01feee429a9ffec154c0e Mon Sep 17 00:00:00 2001 From: erogol Date: Tue, 12 May 2020 13:46:16 +0200 Subject: [PATCH] config remove empty chars --- config.json | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/config.json b/config.json index da3fe286..c23bd004 100644 --- a/config.json +++ b/config.json @@ -1,5 +1,5 @@ { - "model": "Tacotron2", + "model": "Tacotron2", "run_name": "ljspeech", "run_description": "tacotron2", @@ -11,12 +11,12 @@ "hop_length": 256, // stft window hop-lengh in ms. "frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used. "frame_shift_ms": null, // stft window hop-lengh in ms. If null, 'hop_length' is used. - + // Audio processing parameters "sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled. "preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. "ref_level_db": 20, // reference level db, theoretically 20db is the sound of air. - + // Silence trimming "do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) "trim_db": 60, // threshold for timming silence. Set this according to your dataset. @@ -26,7 +26,7 @@ "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation. // MelSpectrogram parameters - "num_mels": 80, // size of the mel spec frame. + "num_mels": 80, // size of the mel spec frame. "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!! @@ -50,7 +50,7 @@ // "punctuations":"!'(),-.:;? ", // "phonemes":"iyɨʉɯuɪʏʊeøɘəɵɤoɛœɜɞʌɔæɐaɶɑɒᵻʘɓǀɗǃʄǂɠǁʛpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟˈˌːˑʍwɥʜʢʡɕʑɺɧɚ˞ɫ" // }, - + // DISTRIBUTED TRAINING "distributed":{ "backend": "nccl", @@ -61,8 +61,8 @@ // 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. + "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, 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. @@ -80,11 +80,11 @@ "wd": 0.000001, // Weight decay weight. "warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr" "seq_len_norm": false, // Normalize eash sample loss with its length to alleviate imbalanced datasets. Use it if your dataset is small or has skewed distribution of sequence lengths. - + // 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. + "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. "prenet_type": "original", // "original" or "bn". - "prenet_dropout": true, // enable/disable dropout at prenet. + "prenet_dropout": true, // enable/disable dropout at prenet. // ATTENTION "attention_type": "original", // 'original' or 'graves' @@ -98,16 +98,16 @@ "bidirectional_decoder": false, // use https://arxiv.org/abs/1907.09006. Use it, if attention does not work well with your dataset. // STOPNET - "stopnet": true, // Train stopnet predicting the end of synthesis. + "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. - "print_eval": false, // If True, it prints loss values in evalulation. + "print_eval": false, // If True, it prints loss values in evalulation. "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. - + "tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. + // DATA LOADING "text_cleaner": "phoneme_cleaners", "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars. @@ -119,7 +119,7 @@ // PATHS "output_path": "/home/erogol/Models/LJSpeech/", - + // PHONEMES "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.