diff --git a/config_kusal.json b/config_kusal.json deleted file mode 100644 index 696171f..0000000 --- a/config_kusal.json +++ /dev/null @@ -1,41 +0,0 @@ -{ - "model_name": "TTS-larger-kusal", - "audio_processor": "audio", - "num_mels": 80, - "num_freq": 1025, - "sample_rate": 22000, - "frame_length_ms": 50, - "frame_shift_ms": 12.5, - "preemphasis": 0.97, - "min_mel_freq": 125, - "max_mel_freq": 7600, - "min_level_db": -100, - "ref_level_db": 20, - "embedding_size": 256, - "text_cleaner": "english_cleaners", - - "epochs": 1000, - "lr": 0.002, - "lr_decay": 0.5, - "decay_step": 100000, - "warmup_steps": 4000, - "batch_size": 32, - "eval_batch_size":-1, - "r": 5, - - "griffin_lim_iters": 60, - "power": 1.5, - - "num_loader_workers": 8, - - "checkpoint": true, - "save_step": 25000, - "print_step": 10, - "run_eval": false, - "data_path": "/snakepit/shared/data/mycroft/kusal/", - "meta_file_train": "prompts.txt", - "meta_file_val": null, - "dataset": "Kusal", - "min_seq_len": 0, - "output_path": "../keep/" -} \ No newline at end of file diff --git a/config_libritts.json b/config_libritts.json deleted file mode 100644 index 658b983..0000000 --- a/config_libritts.json +++ /dev/null @@ -1,82 +0,0 @@ -{ - "run_name": "libritts-360", - "run_description": "LibriTTS 360 gradual traning with memory queue.", - - "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": false, // move normalization to range [-1, 1] - "max_norm": 1, // 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": 7, // ONLY TACOTRON - memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5. - "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, // enable/disable 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. - "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": true, // 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. - "eval_batch_size":16, - "r": 7, // Number of frames to predict for step. - "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 traning stats and checkpoints. - "print_step": 10, // 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/erogol/Data/Libri-TTS/train-clean-360/", // DATASET-RELATED: can overwritten from command argument - "meta_file_train": null, // DATASET-RELATED: metafile for training dataloader. - "meta_file_val": null, // DATASET-RELATED: metafile for evaluation dataloader. - "dataset": "libri_tts", // 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": "/media/erogol/data_ssd/Models/libri_tts/", // DATASET-RELATED: output path for all training outputs. - "num_loader_workers": 12, // 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": true -} - diff --git a/server/__init__.py b/server/__init__.py new file mode 100644 index 0000000..e69de29