[Bug] AttributeError: module 'TTS.tts.datasets' has no attribute ''

[ban1989ban]

Trying to finetune:(I have created datset in my voice). Issue here is dataset_name & formatter name seems empty(at least that's what I think)

config.json

{
"model": "glow_tts",
"run_name": "glow-tts-rel_pos_transformer",
"run_description": "glow-tts model training with relation position transformer encoder.",

    // AUDIO PARAMETERS
    "audio":{
        "fft_size": 1024,         // 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
        "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": 0,     // reference level db, theoretically 20db is the sound of air.

        // Griffin-Lim
        "power": 1.1,           // 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.

        // 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.

        // MelSpectrogram parameters
        "num_mels": 80,         // size of the mel spec frame.
        "mel_fmin": 50.0,        // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
        "mel_fmax": 7600.0,     // maximum freq level for mel-spec. Tune for dataset!!
        "spec_gain": 1.0,         // scaler value appplied after log transform of spectrogram.00

        // Normalization parameters
        "signal_norm": false,   // 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]
        "clip_norm": true,      // clip normalized values into the range.
        "stats_path": null    // 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": "abcdefhijklmnopqrstuvwxyz\u00e6\u00e7\u00f0\u00f8\u0127\u014b\u0153\u01c0\u01c1\u01c2\u01c3\u0250\u0251\u0252\u0253\u0254\u0255\u0256\u0257\u0258\u0259\u025a\u025b\u025c\u025e\u025f\u0260\u0261\u0262\u0263\u0264\u0265\u0266\u0267\u0268\u026a\u026b\u026c\u026d\u026e\u026f\u0270\u0271\u0272\u0273\u0274\u0275\u0276\u0278\u0279\u027a\u027b\u027d\u027e\u0280\u0281\u0282\u0283\u0284\u0288\u0289\u028a\u028b\u028c\u028d\u028e\u028f\u0290\u0291\u0292\u0294\u0295\u0298\u0299\u029b\u029c\u029d\u029f\u02a1\u02a2\u02c8\u02cc\u02d0\u02d1\u02de\u03b2\u03b8\u03c7\u1d7b\u2c71"
    },

    "add_blank": false, // if true add a new token after each token of the sentence. This increases the size of the input sequence, but has considerably improved the prosody of the GlowTTS model.

    // 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.

    // MODEL PARAMETERS
    // "use_mas": false,       // use Monotonic Alignment Search if true. Otherwise use pre-computed attention alignments.
    "hidden_channels_encoder": 192,
    "hidden_channels_decoder": 192,
    "hidden_channels_duration_predictor": 256,
    "use_encoder_prenet": true,
    "encoder_type": "rel_pos_transformer",
    "encoder_params": {
        "kernel_size":3,
        "dropout_p": 0.1,
        "num_layers": 6,
        "num_heads": 2,
        "hidden_channels_ffn": 768,
        "input_length": null
    },

    // TRAINING
    "batch_size": 1,       // 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": 1,                 // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
    "loss_masking": true,   // enable / disable loss masking against the sequence padding.
    "mixed_precision": true,
    "data_dep_init_iter": 10,

    // VALIDATION
    "run_eval": true,
    "test_delay_epochs": 0,       //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": true,         // use noam warmup and lr schedule.
    "grad_clip": 5.0,              // upper limit for gradients for clipping.
    "epochs": 10000,               // total number of epochs to train.
    "lr": 1e-3,                    // Initial learning rate. If Noam decay is active, maximum learning rate.
    "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.

    // TENSORBOARD and LOGGING
    "print_step": 1,       // Number of steps to log training on console.
    "tb_plot_step": 100,    // Number of steps to plot TB training figures.
    "print_eval": false,     // If True, it prints intermediate loss values in evalulation.
    "save_step": 5000,      // 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": 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.
    "batch_group_size": 0,  //Number of batches to shuffle after bucketing.
    "min_seq_len": 3,       // DATASET-RELATED: minimum text length to use in training
    "max_seq_len": 500,     // DATASET-RELATED: maximum text length
    "compute_f0": false,     // compute f0 values in data-loader
    "use_noise_augment": true,  //add a random noise to audio signal for augmentation at training .
    "compute_input_seq_cache": true,

    // PATHS
    "output_path": "/content/drive/MyDrive/TTS/finetune/output/",

    // PHONEMES
    "phoneme_cache_path": "/content/drive/MyDrive/TTS/finetune/phoneme_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
    "phonemizer": "gruut",

    // MULTI-SPEAKER and GST
    "use_speaker_embedding": false,     // use speaker embedding to enable multi-speaker learning.
    "use_external_speaker_embedding_file": false,
    "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": "/content/drive/MyDrive/TTS/finetune/",
                "meta_file_train": "/content/drive/MyDrive/TTS/finetune/metadata.txt",
                "meta_file_val": null
                // "path_for_attn": "/home/erogol/Data/LJSpeech-1.1/alignments/"
            }
        ]
}

Command:

!CUDA_VISIBLE_DEVICES="0" python TTS/bin/train_tts.py
--config_path /content/drive/MyDrive/TTS/finetune/config.json
--restore_path /content/drive/MyDrive/TTS/finetune/model_file.pth

Error:
Traceback (most recent call last):
File "/content/drive/MyDrive/TTS/TTS/bin/train_tts.py", line 73, in
main()
File "/content/drive/MyDrive/TTS/TTS/bin/train_tts.py", line 49, in main
train_samples, eval_samples = load_tts_samples(
^^^^^^^^^^^^^^^^^
File "/content/drive/MyDrive/TTS/TTS/tts/datasets/init.py", line 118, in load_tts_samples
formatter = _get_formatter_by_name(formatter_name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/content/drive/MyDrive/TTS/TTS/tts/datasets/init.py", line 166, in _get_formatter_by_name
return getattr(thismodule, name.lower())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: module 'TTS.tts.datasets' has no attribute ''

[eginhard]

Correct, you have to specify a formatter name, so that Coqui knows how to load your data.