From 777bc38b4e0a2b5ab7e2f22029972246c3d10b1e Mon Sep 17 00:00:00 2001 From: root Date: Fri, 20 Dec 2019 15:18:21 +0000 Subject: [PATCH] remove old configs --- config_tacotron.json | 82 --------------------------------------- config_tacotron2.json | 84 ---------------------------------------- config_tacotron_de.json | 82 --------------------------------------- config_tacotron_gst.json | 83 --------------------------------------- 4 files changed, 331 deletions(-) delete mode 100644 config_tacotron.json delete mode 100644 config_tacotron2.json delete mode 100644 config_tacotron_de.json delete mode 100644 config_tacotron_gst.json diff --git a/config_tacotron.json b/config_tacotron.json deleted file mode 100644 index 92ee3909..00000000 --- a/config_tacotron.json +++ /dev/null @@ -1,82 +0,0 @@ -{ - "run_name": "mozilla-tacotron-tagent-bn", - "run_description": "compare the attention with gst model which does not align with the same config", - - "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": 22050, // 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" - "windowing": false, // Enables attention windowing. Used only in eval mode. - "memory_size": 5, // 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. - "use_forward_attn": true, // enable/disable forward attention. In general, it aligns faster. - "forward_attn_mask": false, // Apply forward attention mask af inference to prevent bad modes. Try it if your model does not align well. - "transition_agent": true, // enable/disable transition agent of forward attention. - "location_attn": false, // 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": 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. - "eval_batch_size":16, - "r": 5, // 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, - "data_path": "/media/erogol/data_ssd/Data/Mozilla/", // DATASET-RELATED: can overwritten from command argument - "meta_file_train": "metadata_train.txt", // DATASET-RELATED: metafile for training dataloader. - "meta_file_val": "metadata_val.txt", // DATASET-RELATED: metafile for evaluation dataloader. - "dataset": "mozilla", // 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": 0, // 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": 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": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages - "text_cleaner": "phoneme_cleaners", - "use_speaker_embedding": false // whether to use additional embeddings for separate speakers - } - \ No newline at end of file diff --git a/config_tacotron2.json b/config_tacotron2.json deleted file mode 100644 index 02b4341b..00000000 --- a/config_tacotron2.json +++ /dev/null @@ -1,84 +0,0 @@ -{ - "run_name": "mozilla-no-loc-fattn-stopnet-sigmoid-loss_masking", - "run_description": "using forward attention, with original prenet, loss masking,separate stopnet, sigmoid. Compare this with 4817. Pytorch DPP", - - "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": 22050, // 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": "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 - 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. - "use_forward_attn": true, // enable/disable forward attention. In general, it aligns faster. - "forward_attn_mask": false, // Apply forward attention mask af inference to prevent bad modes. Try it if your model does not align well. - "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. - - "windowing": false, // Enables attention windowing. Used only in eval mode. - "forward_attn_masking": false, // Enable forward attention masking which improves attention stability. Use it if network does not work as you like when it is off. - - "batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. - "eval_batch_size":16, - "r": 1, // 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": "/media/erogol/data_ssd/Data/Mozilla/", // DATASET-RELATED: can overwritten from command argument - "meta_file_train": "metadata_train.txt", // DATASET-RELATED: metafile for training dataloader. - "meta_file_val": "metadata_val.txt", // DATASET-RELATED: metafile for evaluation dataloader. - "dataset": "mozilla", // 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": 0, // 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": 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": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages - "text_cleaner": "phoneme_cleaners", - "use_speaker_embedding": false // whether to use additional embeddings for separate speakers - } - diff --git a/config_tacotron_de.json b/config_tacotron_de.json deleted file mode 100644 index fc3efbec..00000000 --- a/config_tacotron_de.json +++ /dev/null @@ -1,82 +0,0 @@ -{ - "run_name": "german-all-tacotrongst", - "run_description": "train with all the german dataset using gst", - - "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": "TacotronGST", // one of the model in models/ - "grad_clip": 1, // upper limit for gradients for clipping. - "epochs": 10000, // 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" - "windowing": false, // Enables attention windowing. Used only in eval mode. - "memory_size": 5, // 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. - "use_forward_attn": false, // enable/disable forward attention. In general, it aligns faster. - "transition_agent": false, // enable/disable transition agent of forward attention. - "forward_attn_mask": false, // Apply forward attention mask at inference to prevent bad modes. Try it if your model does not align well. - "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. - "eval_batch_size":32, - "r": 5, // 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": false, - "test_sentences_file": "de_sentences.txt", // set a file to load sentences to be used for testing. If it is null then we use default english sentences. - "test_delay_epochs": 5, //Until attention is aligned, testing only wastes computation time. - "data_path": "/home/erogol/Data/m-ai-labs/de_DE/by_book/" , // 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": "mailabs", // 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": 15, // DATASET-RELATED: minimum text length to use in training - "max_seq_len": 200, // DATASET-RELATED: maximum text length - "output_path": "/home/erogol/Models/mozilla_models/", // 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": "phoneme_cache", // 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": "de", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages - "text_cleaner": "phoneme_cleaners", - "use_speaker_embedding": false // whether to use additional embeddings for separate speakers - } - \ No newline at end of file diff --git a/config_tacotron_gst.json b/config_tacotron_gst.json deleted file mode 100644 index e56c85dd..00000000 --- a/config_tacotron_gst.json +++ /dev/null @@ -1,83 +0,0 @@ -{ - "run_name": "mozilla-tacotron-gst", - "run_description": "GST with single speaker", - - "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": 22050, // 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": "TacotronGST", // one of the model in models/ - "grad_clip": 1, // upper limit for gradients for clipping. - "epochs": 10000, // 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" - "windowing": false, // Enables attention windowing. Used only in eval mode. - "memory_size": 5, // 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. - "use_forward_attn": true, // enable/disable forward attention. In general, it aligns faster. - "forward_attn_mask": false, // Apply forward attention mask at inference to prevent bad modes. Try it if your model does not align well. - "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. - "eval_batch_size":16, - "r": 5, // 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, - "data_path": "/media/erogol/data_ssd/Data/Mozilla/", // DATASET-RELATED: can overwritten from command argument - "meta_file_train": "metadata_train.txt", // DATASET-RELATED: metafile for training dataloader. - "meta_file_val": "metadata_val.txt", // DATASET-RELATED: metafile for evaluation dataloader. - "dataset": "mozilla", // 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": 0, // 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": 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": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages - "text_cleaner": "phoneme_cleaners", - "use_speaker_embedding": false, // whether to use additional embeddings for separate speakers - "style_wav_for_test": null // path to wav for styling the inference tests when using GST - } - \ No newline at end of file