No need to be sorry; the wav is 5 words long and some kb’s. The problem isn’t the file itself; the whole dataset isn’t read (mine or LJSpeech). First, it complains about sentences where numbers are present. Then, I remove these sentences with a script (csv file and wav’s). Then it complains about sentences with 1 word. Remove these and it complains about sentences with 2 words. I removed all sentences with length less than 5 and it still complains and I have also set the minimum seq length to 0. The files are not read. The model was trained on the dev branch, which is also the one I checked out in. This is my config:
{
“github_branch”:"* dev",
//“restore_path”:"/data/rw/pit/keep/ljspeech-December-11-2019_04+32PM-ca49ae8/checkpoint_410000.pth.tar",
“github_branch”:"* dev",
“model”: “Tacotron2”, // one of the model in models/
“run_name”: “ljspeech-bn”,
“run_description”: “tacotron2 basline finetuned with BN prenet”,
// AUDIO PARAMETERS
"audio":{
// Audio processing parameters
"trim_db": 0,
"mulaw": true,
"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, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
"frame_length_ms": 10.0, // stft window length in ms.
"frame_shift_ms": 2.0, // 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.
"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.
"griffin_lim_iters": 60, // #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
// 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]
"clip_norm": true, // clip normalized values into the range.
"mel_fmin": 50.0, // 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)
},
// DISTRIBUTED TRAINING
"distributed":{
"backend": "nccl",
"url": "tcp:\/\/localhost:54321"
},
"reinit_layers": [], // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.
// 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, 32]], // ONLY TACOTRON - set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled.
"loss_masking": true, // enable / disable loss masking against the sequence padding.
// VALIDATION
"run_eval": true,
"test_delay_epochs": 10, //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
"noam_schedule": false,
"grad_clip": 1.0, // 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.
"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,
// 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.
"prenet_type": "bn", // "original" or "bn".
"prenet_dropout": false, // enable/disable dropout at prenet.
// ATTENTION
"attention_type": "original", // 'original' or 'graves'
"attention_heads": 5, // number of attention heads (only for 'graves')
"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, // 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.
// 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.
// DATA LOADING
"text_cleaner": "phoneme_cleaners",
"enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
"num_loader_workers": 5, // 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": 1, // DATASET-RELATED: minimum text length to use in training
"max_seq_len": 150, // DATASET-RELATED: maximum text length
// PATHS
"output_path": "/data/rw/pit/keep/", // DATASET-RELATED: output path for all training outputs.
//"output_path": "/media/erogol/data_ssd/Models/runs/",
// PHONEMES
"phoneme_cache_path": "ljspeech_ph_cache", // 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
// 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.
[
{
"name": "ljspeech",
"path": "/home/georgios_roussos/TTS/LJSpeech-1.1/",
//"path": "/home/erogol/Data/LJSpeech-1.1",
"meta_file_train": "metadata_train.csv",
"meta_file_val": "metadata_val.csv"
}
]
}
I would really like to see how the model performs when re-trained on a new voice, because the performance it achieves on LJSpeech is very impressive and I am doing research on speaker adaptation.
