Replies: 1 comment
-
>>> georroussos |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
>>> fatih_kiralioglu
[February 4, 2020, 2:13pm]
Hello, slash
I have tried a Tacotron2 training with a custom configuration using the
my own voice database slash
Unfortunately, the test synthesis results are not good and only 2 out of
4 test synthesis records are intelligible. slash
I guess that there is a very basic error causing this behavior but I
couldn't figure it out. slash
I hare the config file content below.
I also note that I could get very good synthesis results with Tacotron1
method and default config
Any help is appreciated. slash
Best Regards.
{ slash
'github_branch':'inside_docker', slash
'restore_path': slash '/mnt/lvm/MozillaTTS/english_tts/TTS-master-gpu_melissa_2/keep/ljspeech-January-10-2020_09+47AM-0000000/checkpoint_50000.pth.tar slash ', slash
'run_name': 'ljspeech', slash
'run_description': 'Tacotron2 ljspeech release training',
'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': 60.0, // 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': false // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
},
'distributed':{
'backend': 'nccl',
'url': 'tcp: slash / slash /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': 5, // 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': true, // 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': false, // 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': 1, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
'gradual_training': null, //[[0, 7, 32], [1, 5, 32], [50000, 3, 32], [230000, 2, 16], [390000, 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 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': 5, // DATASET-RELATED: minimum text length to use in training
'max_seq_len': 150, // DATASET-RELATED: maximum text length
'output_path': 'keep/', // DATASET-RELATED: output path for all training outputs.
'num_loader_workers': 8, // 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': 'en-us', // 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': '/mnt/lvm/MozillaTTS/english_tts/melissa_all_trimmed',
'meta_file_train': 'metadata_train.csv',
'meta_file_val': 'metadata_val.csv'
}
]
}
[This is an archived TTS discussion thread from discourse.mozilla.org/t/tacotron2-bad-test-synthesis-results]
Beta Was this translation helpful? Give feedback.
All reactions