From 0ee1dd54a377e2062fd98141410f26a75ddcc213 Mon Sep 17 00:00:00 2001 From: erogol Date: Tue, 17 Mar 2020 12:44:18 +0100 Subject: [PATCH] config update for mean-var scaling --- config.json | 60 +++++++++++++++++++++++++++++++---------------------- 1 file changed, 35 insertions(+), 25 deletions(-) diff --git a/config.json b/config.json index efc96c9e..1b497646 100644 --- a/config.json +++ b/config.json @@ -1,45 +1,55 @@ { - "model": "Tacotron2", // one of the model in models/ + "model": "Tacotron2", "run_name": "ljspeech", "run_description": "tacotron2 with guided attention and -1 1 normalization and no preemphasis", // AUDIO PARAMETERS "audio":{ + // stft parameters + "num_freq": 513, // number of stft frequency levels. Size of the linear spectogram frame. + "win_length": 1024, // stft window length in ms. + "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 - "num_mels": 80, // size of the mel spec 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": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. - "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. - "min_level_db": -100, // normalization range + "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. + + // Griffin-Lim "power": 1.5, // value to sharpen wav signals after GL algorithm. "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. + "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!! + // Normalization parameters - "signal_norm": true, // normalize the spec values in range [0, 1] + "signal_norm": true, // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params. + "min_level_db": -100, // lower bound for normalization "symmetric_norm": true, // move normalization to range [-1, 1] - "max_norm": 1.0, // 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!! - "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. + "stats_path": "/home/erogol/Data/LJSpeech-1.1/scale_stats.npy" // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored }, // VOCABULARY PARAMETERS // if custom character set is not defined, // default set in symbols.py is used - "characters":{ - "pad": "_", - "eos": "~", - "bos": "^", - "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ", - "punctuations":"!'(),-.:;? ", - "phonemes":"iyɨʉɯuɪʏʊeøɘəɵɤoɛœɜɞʌɔæɐaɶɑɒᵻʘɓǀɗǃʄǂɠǁʛpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟˈˌːˑʍwɥʜʢʡɕʑɺɧɚ˞ɫ" - }, + // "characters":{ + // "pad": "_", + // "eos": "~", + // "bos": "^", + // "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ", + // "punctuations":"!'(),-.:;? ", + // "phonemes":"iyɨʉɯuɪʏʊeøɘəɵɤoɛœɜɞʌɔæɐaɶɑɒᵻʘɓǀɗǃʄǂɠǁʛpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟˈˌːˑʍwɥʜʢʡɕʑɺɧɚ˞ɫ" + // }, // DISTRIBUTED TRAINING "distributed":{ @@ -107,7 +117,7 @@ "max_seq_len": 153, // DATASET-RELATED: maximum text length // PATHS - "output_path": "/data4/rw/home/Trainings/", + "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. @@ -124,7 +134,7 @@ [ { "name": "ljspeech", - "path": "/root/LJSpeech-1.1/", + "path": "/home/erogol/Data/LJSpeech-1.1/", "meta_file_train": "metadata.csv", "meta_file_val": null }