Macedonian voice for tts

[JRMeyer]

>>> Ivona_Milanova
[March 13, 2020, 6:44am]

Hi, slash
I am creating a TTS for Macedonian Language. I have collected 9 hours of
data and I am training a Tacotron model.

This is the alignment I get after 128000 steps. However I get noise at
the end of the train file. Is this caused because of silences at the end
of audio files?

178

This is the configuration I am using:

'audio':{ slash
// Audio processing parameters slash
'num_mels': 80, // size of the mel spec frame. slash
'num_freq': 1025, // number of stft frequency levels. Size of the linear
spectogram frame. slash
'sample_rate': 22050, // DATASET-RELATED: wav sample-rate. If different
than the original data, it is resampled. slash
'frame_length_ms': 50, // stft window length in ms. slash
'frame_shift_ms': 12.5, // stft window hop-lengh in ms. slash
'preemphasis': 0.98, // pre-emphasis to reduce spec noise and make it
more structured. If 0.0, no -pre-emphasis. slash
'min_level_db': -100, // normalization range slash
'ref_level_db': 20, // reference level db, theoretically 20db is the
sound of air. slash
'power': 1.5, // value to sharpen wav signals after GL algorithm. slash
'griffin_lim_iters': 60,// [ slash #griffin-lim] iterations. 30-60
is a good range. Larger the value, slower the generation. slash
// Normalization parameters slash
'signal_norm': true, // normalize the spec values in range slash [0, 1 slash ] slash
'symmetric_norm': true, // move normalization to range slash [-1, 1 slash ] slash
'max_norm': 4, // scale normalization to range slash [-max_norm, max_norm slash ]
or slash [0, max_norm slash ] slash
'clip_norm': true, // clip normalized values into the range. slash
'mel_fmin': 0.0, // minimum freq level for mel-spec. slash ~50 for male and
slash ~95 for female voices. Tune for dataset!! slash
'mel_fmax': 8000.0, // maximum freq level for mel-spec. Tune for
dataset!! slash
'do_trim_silence': false // enable trimming of slience of audio as you
load it. LJspeech (false), TWEB (false), Nancy (true) slash
},

'distributed':{
'backend': 'nccl',
'url': 'tcp: slash / slash /localhost:54321'
},

'reinit_layers': [],

'model': 'Tacotron', // one of the model in models/
'grad_clip': 1, // upper limit for gradients for clipping.
'epochs': 3000, // 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], [1, 5, 32], [50000, 3, 32], [130000, 2, 16], [290000, 1, 16]], // 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': 1000, // 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': 9, // DATASET-RELATED: minimum text length to use in training
'max_seq_len': 182, // DATASET-RELATED: maximum text length
'output_path': '../keep/', // DATASET-RELATED: output path for all training outputs.
'num_loader_workers': 2, // number of training data loader processes. Don't set it too big. 4-8 are good values.
'num_val_loader_workers': 2, // number of evaluation data loader processes.
'phoneme_cache_path': 'mozilla_mk_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': 'mk', // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages
'text_cleaner': 'basic_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': '',
'path': '',
'meta_file_train': 'metadata_train.csv',
'meta_file_val': 'metadata_val.csv'
}
]

[This is an archived TTS discussion thread from discourse.mozilla.org/t/macedonian-voice-for-tts]

[JRMeyer]

>>> dkreutz
[March 13, 2020, 8:35am]

> 'do_trim_silence': false

Try with setting 'do_trim_silence: true'

While you at it you might also want to adapt mel_fmin and mel_fmax
setting, e.g. 'mel_fmin': 50.0

[Archived Post]

[JRMeyer]

>>> sanjaesc
[March 13, 2020, 9:20am]

Do you get the same noise when generating sentences? If not then you
should be fine.

[Archived Post]

[JRMeyer]

>>> georroussos
[March 13, 2020, 10:14am]

That noise you will only be probably get during training time, not
inference.

[Archived Post]

[JRMeyer]

>>> erogol
[March 15, 2020, 2:45pm]

noise in training time is normal due to padding

[Archived Post]