Need help on Tacotron2 assertion error on wav file

Hi there!

I’m using dev branch to train Tacotron2 on a new Chinese tts dataset. While training, an assertion error occurred and related to one specific .wav file.

I looked into that wav file, it turns out to include only numbers, and the corresponding text looks like “5123489…”, which might be the case but I don’t know how to fix it.

However, I trained tacotron of master branch several days before, and it was all good.

config.json (master tacotron):

{
“run_name”: “zc360_wavenet”,
“run_description”: “gradual training with prenet frame size 1 + no maxout for cbhg + symmetric norm.”,

"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.
    "sample_rate": 16000,   // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
    "frame_length_ms": 50,  // stft window length in ms.
    "frame_shift_ms": 12.5, // 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,          // 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)
},

"distributed":{
    "backend": "nccl",
    "url": "tcp:\/\/localhost:54321"
},

"reinit_layers": [],

"model": "Tacotron",          // one of the model in models/    
"grad_clip": 1,                // 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.
"warmup_steps": 4000,          // Noam decay steps to increase the learning rate from 0 to "lr"
"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. 
"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, 
"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.
"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": 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.
"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, 32], [10000, 5, 32], [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 traning 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.
"data_path": "/home/data1/yutao/tts_data/zc360/",  // DATASET-RELATED: can overwritten from command argument
"meta_file_train": "metadata_train.csv",      // DATASET-RELATED: metafile for training dataloader.
"meta_file_val": "metadata_val.csv",    // DATASET-RELATED: metafile for evaluation dataloader.
"dataset": "ljspeech",      // DATASET-RELATED: one of TTS.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py
"min_seq_len": 6,       // DATASET-RELATED: minimum text length to use in training
"max_seq_len": 150,     // DATASET-RELATED: maximum text length
"output_path": "../zc360_keep/",      // DATASET-RELATED: output path for all training outputs.
"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.
"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": "zh",     // depending on your target language, pick one from  https://github.com/bootphon/phonemizer#languages
"text_cleaner": "phoneme_cleaners",
"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.

}

config.json (dev tacotron2):

{
“run_name”: “zc360”,
“run_description”: “Tacotron prenet fix test run - dev-memory_fix”,

"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.
    "sample_rate": 16000,   // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
    "frame_length_ms": 50,  // stft window length in ms.
    "frame_shift_ms": 12.5, // 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,          // 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)
},

"distributed":{
    "backend": "nccl",
    "url": "tcp:\/\/localhost:54321"
},

"reinit_layers": [],

"model": "Tacotron2",          // one of the model in models/    
"grad_clip": 1,                // 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.
"warmup_steps": 4000,          // Noam decay steps to increase the learning rate from 0 to "lr"
"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": "softmax",   // 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. 
"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, 
"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.
"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": 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.
"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, 32], [1, 5, 32], [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.
“gradual_training”: null,
“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": "../zc360_keep/",      // DATASET-RELATED: output path for all training outputs.
"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.
"phoneme_cache_path": "mozilla_us_phonemes",  // phoneme computation is slow, therefore, it caches results in the given folder.
"use_phonemes": false,           // use phonemes instead of raw characters. It is suggested for better pronounciation.
"phoneme_language": "zh",     // depending on your target language, pick one from  https://github.com/bootphon/phonemizer#languages
"text_cleaner": "phoneme_cleaners",
"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":   // List of datasets. They all merged and they get different speaker_ids.
    [
        {
            "name": "ljspeech",
            "path": "/../../data1/yutao/tts_data/zc360_yanli/",
            "meta_file_train": "metadata_train.csv",
            "meta_file_val": "metadata_val.csv"
        }
    ]

}

Thanks!

Maybe I’m missing something, but would it not just be easier to remove the problem .wav file from your dataset?

Otherwise you could look through the source code of the dataloader in the torch module and see what the assert is being triggered by.