Upload 25 files

tts/tts_models--en--ljspeech--fast_pitch/config.json

@@ -0,0 +1,163 @@
+{
+    "model": "fast_pitch",
+    "run_name": "fast_pitch_ljspeech",
+    "run_description": "",
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "mixed_precision": false,
+    "scheduler_after_epoch": false,
+    "run_eval": true,
+    "test_delay_epochs": -1,
+    "print_eval": false,
+    "dashboard_logger": "tensorboard",
+    "print_step": 50,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "project_name": null,
+    "log_model_step": null,
+    "wandb_entity": null,
+    "save_step": 10000,
+    "checkpoint": true,
+    "keep_all_best": false,
+    "keep_after": 10000,
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 4,
+    "use_noise_augment": false,
+    "output_path": "/home/ubuntu/TTS/recipes/ljspeech/fast_pitch",
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log",
+        "do_trim_silence": true,
+        "trim_db": 60.0,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000,
+        "spec_gain": 1.0,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "signal_norm": false,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": true,
+    "phonemizer": "gruut",
+    "phoneme_language": "en-us",
+    "compute_input_seq_cache": true,
+    "text_cleaner": "english_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/home/ubuntu/TTS/recipes/ljspeech/fast_pitch/phoneme_cache",
+    "characters": {
+        "pad": "_",
+        "eos": "~",
+        "bos": "^",
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u025a\u02de\u026b"
+    },
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "sort_by_audio_len": true,
+    "min_seq_len": 13,
+    "max_seq_len": 500000,
+    "compute_f0": true,
+    "compute_linear_spec": false,
+    "add_blank": false,
+    "datasets": [
+        {
+            "name": "ljspeech",
+            "path": "/home/ubuntu/TTS/recipes/ljspeech/fast_pitch/../LJSpeech-1.1/",
+            "meta_file_train": "metadata.csv",
+            "ununsed_speakers": null,
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "optimizer": "Adam",
+    "optimizer_params": {
+        "betas": [
+            0.9,
+            0.998
+        ],
+        "weight_decay": 1e-06
+    },
+    "lr_scheduler": "NoamLR",
+    "lr_scheduler_params": {
+        "warmup_steps": 4000
+    },
+    "test_sentences": [
+        "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
+        "Be a voice, not an echo.",
+        "I'm sorry Dave. I'm afraid I can't do that.",
+        "This cake is great. It's so delicious and moist.",
+        "Prior to November 22, 1963."
+    ],
+    "use_speaker_embedding": false,
+    "use_d_vector_file": false,
+    "d_vector_dim": 0,
+    "model_args": {
+        "num_chars": null,
+        "out_channels": 80,
+        "hidden_channels": 384,
+        "num_speakers": 0,
+        "duration_predictor_hidden_channels": 256,
+        "duration_predictor_kernel_size": 3,
+        "duration_predictor_dropout_p": 0.1,
+        "pitch_predictor_hidden_channels": 256,
+        "pitch_predictor_kernel_size": 3,
+        "pitch_predictor_dropout_p": 0.1,
+        "pitch_embedding_kernel_size": 3,
+        "positional_encoding": true,
+        "poisitonal_encoding_use_scale": true,
+        "length_scale": 1,
+        "encoder_type": "fftransformer",
+        "encoder_params": {
+            "hidden_channels_ffn": 1024,
+            "num_heads": 1,
+            "num_layers": 6,
+            "dropout_p": 0.1
+        },
+        "decoder_type": "fftransformer",
+        "decoder_params": {
+            "hidden_channels_ffn": 1024,
+            "num_heads": 1,
+            "num_layers": 6,
+            "dropout_p": 0.1
+        },
+        "use_d_vector": false,
+        "d_vector_dim": 0,
+        "detach_duration_predictor": false,
+        "max_duration": 75,
+        "use_aligner": true
+    },
+    "d_vector_file": false,
+    "lr": 0.0001,
+    "grad_clip": 5.0,
+    "ssim_loss_alpha": 1.0,
+    "dur_loss_alpha": 1.0,
+    "spec_loss_alpha": 1.0,
+    "pitch_loss_alpha": 1.0,
+    "aligner_loss_alpha": 1.0,
+    "binary_align_loss_alpha": 1.0,
+    "binary_align_loss_start_step": 20000,
+    "r": 1,
+    "f0_cache_path": "/home/ubuntu/TTS/recipes/ljspeech/fast_pitch/f0_cache"
+}

tts/tts_models--en--ljspeech--fast_pitch/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1779ef4ef9f9f3c016efee5925c0742393eb7c7183f6daae1928b88cbef294b8
+size 458065485

tts/tts_models--en--ljspeech--glow-tts/config.json

@@ -0,0 +1,150 @@
+{
+        "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": 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.
+        "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": 25,       // 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": "/home/erogol/Models/LJSpeech/",
+
+        // PHONEMES
+        "phoneme_cache_path": "/home/erogol/Models/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": "/home/erogol/Data/LJSpeech-1.1/",
+                    "meta_file_train": "metadata.csv",
+                    "meta_file_val": null
+                    // "path_for_attn": "/home/erogol/Data/LJSpeech-1.1/alignments/"
+                }
+            ]
+    }
+
+

tts/tts_models--en--ljspeech--glow-tts/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132f8c4d4dcb0307f04f6243139da5eeb170e29b69bc22167680241d8e6f97c8
+size 343840040

tts/tts_models--en--ljspeech--neural_hmm/._model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4a10a7e6d1dc0d52951cb6746ee984a7e4809bfbf84eb56f34afe1d8aeb3e9
+size 212

tts/tts_models--en--ljspeech--neural_hmm/__MACOSX/tts_models--en--ljspeech--neural_hmm/._model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4a10a7e6d1dc0d52951cb6746ee984a7e4809bfbf84eb56f34afe1d8aeb3e9
+size 212

tts/tts_models--en--ljspeech--neural_hmm/config.json

@@ -0,0 +1,172 @@
+{
+    "output_path": "/home/smehta/Projects/TTS/recipes/ljspeech/neuralhmm_tts",
+    "logger_uri": null,
+    "run_name": "neuralhmmtts_ljspeech",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 1,
+    "plot_step": 1,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "log_model_step": null,
+    "save_step": 500,
+    "save_n_checkpoints": 5000000,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": null,
+    "print_eval": true,
+    "test_delay_epochs": -1,
+    "run_eval": true,
+    "run_eval_steps": 100,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "epochs": 1000,
+    "batch_size": 28,
+    "eval_batch_size": 16,
+    "grad_clip": 40000.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "Adam",
+    "optimizer_params": {
+        "weight_decay": 1e-06
+    },
+    "lr_scheduler": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "NeuralHMM_TTS",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 4,
+    "use_noise_augment": false,
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log",
+        "do_trim_silence": true,
+        "trim_db": 60,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000.0,
+        "spec_gain": 1,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 1.0,
+        "signal_norm": false,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": true,
+    "phonemizer": "espeak",
+    "phoneme_language": "en-us",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "phoneme_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/home/smehta/Projects/TTS/recipes/ljspeech/neuralhmm_tts/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u025a\u02de\u026b",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": null,
+        "is_unique": false,
+        "is_sorted": true
+    },
+    "add_blank": false,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "min_audio_len": 512,
+    "max_audio_len": Infinity,
+    "min_text_len": 10,
+    "max_text_len": 500,
+    "compute_f0": false,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 8,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "ljspeech",
+            "dataset_name": "",
+            "path": "data/LJSpeech-1.1/",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        "Be a voice, not an echo."
+    ],
+    "eval_split_max_size": null,
+    "eval_split_size": 0.01,
+    "use_speaker_weighted_sampler": false,
+    "speaker_weighted_sampler_alpha": 1.0,
+    "use_language_weighted_sampler": false,
+    "language_weighted_sampler_alpha": 1.0,
+    "use_length_weighted_sampler": false,
+    "length_weighted_sampler_alpha": 1.0,
+    "force_generate_statistics": false,
+    "mel_statistics_parameter_path": "/home/smehta/Projects/TTS/recipes/ljspeech/neuralhmm_tts/lj_parameters.pt",
+    "num_chars": 131,
+    "state_per_phone": 2,
+    "encoder_in_out_features": 512,
+    "encoder_n_convolutions": 3,
+    "out_channels": 80,
+    "ar_order": 1,
+    "sampling_temp": 0.0,
+    "deterministic_transition": true,
+    "duration_threshold": 0.55,
+    "use_grad_checkpointing": true,
+    "max_sampling_time": 1000,
+    "prenet_type": "original",
+    "prenet_dim": 256,
+    "prenet_n_layers": 2,
+    "prenet_dropout": 0.5,
+    "prenet_dropout_at_inference": true,
+    "memory_rnn_dim": 1024,
+    "outputnet_size": [
+        1024
+    ],
+    "flat_start_params": {
+        "mean": 0.0,
+        "std": 1.0,
+        "transition_p": 0.14
+    },
+    "std_floor": 0.001,
+    "r": 1,
+    "use_d_vector_file": false,
+    "use_speaker_embedding": false,
+    "restore_path": "/home/smehta/Projects/TTS/recipes/ljspeech/neuralhmm_tts/neuralhmmtts_ljspeech-January-09-2023_01+44PM-c56dce6b/checkpoint_158500.pth",
+    "github_branch": "* rebuttal"
+}

tts/tts_models--en--ljspeech--neural_hmm/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0287896bd01519d1d8fa4958680b96ea132d0e630bff5d77bc232eac28515df5
+size 183446015

tts/tts_models--en--ljspeech--overflow/._model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ee90b5a99e2b350b2bfc92daf2518c067aea942f159689542d4a9d5c47288b
+size 212

tts/tts_models--en--ljspeech--overflow/__MACOSX/tts_models--en--ljspeech--overflow/._model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ee90b5a99e2b350b2bfc92daf2518c067aea942f159689542d4a9d5c47288b
+size 212

tts/tts_models--en--ljspeech--overflow/config.json

@@ -0,0 +1,185 @@
+{
+    "output_path": "/data/TTS/recipes/ljspeech/overflow",
+    "logger_uri": null,
+    "run_name": "overflow_ljspeech",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 1,
+    "plot_step": 1,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "log_model_step": null,
+    "save_step": 500,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": null,
+    "print_eval": true,
+    "test_delay_epochs": -1,
+    "run_eval": true,
+    "run_eval_steps": 100,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "epochs": 1000,
+    "batch_size": 30,
+    "eval_batch_size": 16,
+    "grad_clip": 40000.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "Adam",
+    "optimizer_params": {
+        "weight_decay": 1e-06
+    },
+    "lr_scheduler": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "OverFlow",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 4,
+    "use_noise_augment": false,
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log",
+        "do_trim_silence": true,
+        "trim_db": 60.0,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000,
+        "spec_gain": 1.0,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 1.0,
+        "signal_norm": false,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": true,
+    "phonemizer": "espeak",
+    "phoneme_language": "en-us",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "phoneme_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/data/TTS/recipes/ljspeech/overflow/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u025a\u02de\u026b",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": null,
+        "is_unique": false,
+        "is_sorted": true
+    },
+    "add_blank": false,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "compute_f0": false,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 8,
+    "start_by_longest": false,
+    "datasets": [
+        {
+            "formatter": "ljspeech",
+            "dataset_name": "",
+            "path": "data/LJSpeech-1.1/LJSpeech-1.1",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
+        "Be a voice, not an echo.",
+        "I'm sorry Dave. I'm afraid I can't do that.",
+        "This cake is great. It's so delicious and moist.",
+        "Prior to November 22, 1963."
+    ],
+    "eval_split_max_size": null,
+    "eval_split_size": 0.01,
+    "use_speaker_weighted_sampler": false,
+    "speaker_weighted_sampler_alpha": 1.0,
+    "use_language_weighted_sampler": false,
+    "language_weighted_sampler_alpha": 1.0,
+    "use_length_weighted_sampler": false,
+    "length_weighted_sampler_alpha": 1.0,
+    "force_generate_statistics": false,
+    "mel_statistics_parameter_path": "/data/TTS/recipes/ljspeech/overflow/lj_parameters.pt",
+    "num_chars": 131,
+    "state_per_phone": 2,
+    "encoder_in_out_features": 512,
+    "encoder_n_convolutions": 3,
+    "out_channels": 80,
+    "ar_order": 1,
+    "sampling_temp": 0.334,
+    "deterministic_transition": true,
+    "duration_threshold": 0.55,
+    "use_grad_checkpointing": true,
+    "max_sampling_time": 1000,
+    "prenet_type": "original",
+    "prenet_dim": 256,
+    "prenet_n_layers": 2,
+    "prenet_dropout": 0.5,
+    "prenet_dropout_at_inference": false,
+    "memory_rnn_dim": 1024,
+    "outputnet_size": [
+        256,
+        256
+    ],
+    "flat_start_params": {
+        "mean": 0.0,
+        "std": 1.0,
+        "transition_p": 0.14
+    },
+    "std_floor": 0.01,
+    "hidden_channels_dec": 150,
+    "kernel_size_dec": 5,
+    "dilation_rate": 1,
+    "num_flow_blocks_dec": 12,
+    "num_block_layers": 4,
+    "dropout_p_dec": 0.05,
+    "num_splits": 4,
+    "num_squeeze": 2,
+    "sigmoid_scale": false,
+    "c_in_channels": 0,
+    "min_seq_len": 3,
+    "max_seq_len": 500,
+    "r": 1,
+    "use_d_vector_file": false,
+    "use_speaker_embedding": false,
+    "github_branch": "* pr/shivammehta25/2183"
+}

tts/tts_models--en--ljspeech--overflow/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444ed46bc352d550974506d0b7f888d930d2af3adce46dc14ba2b074e8de8750
+size 327250447

tts/tts_models--en--ljspeech--tacotron2-DCA/config.json

@@ -0,0 +1,204 @@
+{
+    "output_path": "/data/rw/home/Trainings/LJSpeech/",
+    "logger_uri": null,
+    "run_name": "ljspeech-dcattn",
+    "project_name": null,
+    "run_description": "tacotron2 with dynamic convolution attention.",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "log_model_step": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": null,
+    "print_eval": false,
+    "test_delay_epochs": 10,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "epochs": 1000,
+    "batch_size": 64,
+    "eval_batch_size": 16,
+    "grad_clip": 0.05,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "RAdam",
+    "optimizer_params": {
+        "betas": [
+            0.9,
+            0.998
+        ],
+        "weight_decay": 1e-06
+    },
+    "lr_scheduler": "NoamLR",
+    "lr_scheduler_params": {
+        "warmup_steps": 4000
+    },
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": true,
+    "training_seed": 54321,
+    "model": "Tacotron2",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log10",
+        "do_trim_silence": true,
+        "trim_db": 60,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 50.0,
+        "mel_fmax": 7600.0,
+        "spec_gain": 1,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 0.0,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": "C:/Users/Torch/AppData/Local\\tts\\tts_models--en--ljspeech--tacotron2-DCA\\scale_stats.npy"
+    },
+    "use_phonemes": true,
+    "phonemizer": "gruut",
+    "phoneme_language": "en-us",
+    "compute_input_seq_cache": true,
+    "text_cleaner": "phoneme_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": null,
+    "phoneme_cache_path": "~/phoneme_cache/",
+    "characters": {
+        "characters_class": null,
+        "vocab_dict": null,
+        "pad": "_",
+        "eos": "~",
+        "bos": "^",
+        "blank": null,
+        "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",
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": false,
+    "batch_group_size": 4,
+    "loss_masking": true,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "compute_f0": false,
+    "compute_energy": false,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "/root/LJSpeech-1.1/",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": null,
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
+        "Be a voice, not an echo.",
+        "I'm sorry Dave. I'm afraid I can't do that.",
+        "This cake is great. It's so delicious and moist.",
+        "Prior to November 22, 1963."
+    ],
+    "eval_split_max_size": null,
+    "eval_split_size": 0.01,
+    "use_speaker_weighted_sampler": false,
+    "speaker_weighted_sampler_alpha": 1.0,
+    "use_language_weighted_sampler": false,
+    "language_weighted_sampler_alpha": 1.0,
+    "use_length_weighted_sampler": false,
+    "length_weighted_sampler_alpha": 1.0,
+    "use_gst": false,
+    "gst": {
+        "gst_style_input_wav": null,
+        "gst_style_input_weights": null,
+        "gst_embedding_dim": 512,
+        "gst_use_speaker_embedding": false,
+        "gst_num_heads": 4,
+        "gst_num_style_tokens": 10
+    },
+    "gst_style_input": null,
+    "use_capacitron_vae": false,
+    "capacitron_vae": null,
+    "num_speakers": 1,
+    "num_chars": 0,
+    "r": 2,
+    "gradual_training": null,
+    "memory_size": -1,
+    "prenet_type": "original",
+    "prenet_dropout": true,
+    "prenet_dropout_at_inference": false,
+    "stopnet": true,
+    "separate_stopnet": true,
+    "stopnet_pos_weight": 15.0,
+    "max_decoder_steps": 500,
+    "encoder_in_features": 512,
+    "decoder_in_features": 512,
+    "decoder_output_dim": 80,
+    "out_channels": 80,
+    "attention_type": "dynamic_convolution",
+    "attention_heads": 4,
+    "attention_norm": "softmax",
+    "attention_win": false,
+    "windowing": false,
+    "use_forward_attn": false,
+    "forward_attn_mask": false,
+    "transition_agent": false,
+    "location_attn": false,
+    "bidirectional_decoder": false,
+    "double_decoder_consistency": false,
+    "ddc_r": 7,
+    "speakers_file": null,
+    "use_speaker_embedding": false,
+    "speaker_embedding_dim": 512,
+    "use_d_vector_file": false,
+    "d_vector_file": false,
+    "d_vector_dim": null,
+    "seq_len_norm": false,
+    "decoder_loss_alpha": 0.25,
+    "postnet_loss_alpha": 0.25,
+    "postnet_diff_spec_alpha": 0.0,
+    "decoder_diff_spec_alpha": 0.0,
+    "decoder_ssim_alpha": 0.25,
+    "postnet_ssim_alpha": 0.25,
+    "ga_alpha": 0.0
+}

tts/tts_models--en--ljspeech--tacotron2-DCA/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe9e59413636dc20955df27f171732996f57c7b060c05818ef61aeaa16910ad
+size 339206517

tts/tts_models--en--ljspeech--tacotron2-DCA/scale_stats.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4a45b935563157509ddbff09f59e4ffea35e1d07f3bbf87ec21484cb275c4a
+size 10491

tts/tts_models--en--ljspeech--vits/config.json

@@ -0,0 +1,203 @@
+{
+    "model": "vits",
+    "run_name": "",
+    "run_description": "",
+    "epochs": 10000,
+    "batch_size": null,
+    "eval_batch_size": null,
+    "mixed_precision": false,
+    "scheduler_after_epoch": true,
+    "run_eval": true,
+    "test_delay_epochs": 0,
+    "print_eval": false,
+    "print_step": 25,
+    "tb_plot_step": 100,
+    "tb_model_param_stats": false,
+    "save_step": 10000,
+    "checkpoint": true,
+    "keep_all_best": false,
+    "keep_after": 10000,
+    "num_loader_workers": null,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "output_path": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log10",
+        "do_trim_silence": true,
+        "trim_db": 45,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "spec_gain": 20,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": true,
+    "phoneme_language": "en",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "phoneme_cleaners",
+    "phonemizer": "espeak",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters":{
+	"characters_class": "TTS.tts.models.vits.VitsCharacters",
+        "pad": "_",
+        "eos": "",
+        "bos": "",
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
+        "punctuations":";:,.!?¡¿—…\"«»“” ",
+        "phonemes":"ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"
+    },
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "min_seq_len": 13,
+    "max_seq_len": 200,
+    "compute_f0": false,
+    "compute_linear_spec": true,
+    "add_blank": true,
+    "datasets": [
+        {
+            "name": "",
+            "path": "",
+            "meta_file_train": "",
+            "ununsed_speakers": null,
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "weight_decay": 0.01
+    },
+    "lr_scheduler": "",
+    "lr_scheduler_params": {},
+    "test_sentences": [
+        "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
+        "Be a voice, not an echo.",
+        "I'm sorry Dave. I'm afraid I can't do that.",
+        "This cake is great. It's so delicious and moist.",
+        "Prior to November 22, 1963."
+    ],
+    "use_speaker_embedding": false,
+    "use_d_vector_file": false,
+    "d_vector_dim": 0,
+    "model_args": {
+        "num_chars": 179,
+        "out_channels": 513,
+        "spec_segment_size": 32,
+        "hidden_channels": 192,
+        "hidden_channels_ffn_text_encoder": 768,
+        "num_heads_text_encoder": 2,
+        "num_layers_text_encoder": 6,
+        "kernel_size_text_encoder": 3,
+        "dropout_p_text_encoder": 0.1,
+        "kernel_size_posterior_encoder": 5,
+        "dilation_rate_posterior_encoder": 1,
+        "num_layers_posterior_encoder": 16,
+        "kernel_size_flow": 5,
+        "dilation_rate_flow": 1,
+        "num_layers_flow": 4,
+        "resblock_type_decoder": "1",
+        "resblock_kernel_sizes_decoder": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes_decoder": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates_decoder": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel_decoder": 512,
+        "upsample_kernel_sizes_decoder": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "use_sdp": true,
+        "noise_scale": 1.0,
+        "inference_noise_scale": 0.667,
+        "length_scale": 1,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 0.8,
+        "max_inference_len": null,
+        "init_discriminator": false,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": false,
+        "num_speakers": 0,
+        "speakers_file": null,
+        "speaker_embedding_channels": 256,
+        "use_d_vector_file": false,
+        "d_vector_dim": 0,
+        "detach_dp_input": true
+    },
+    "grad_clip": [
+        5,
+        5
+    ],
+    "lr_gen": 0.0002,
+    "lr_disc": 0.0002,
+    "lr_scheduler_gen": "ExponentialLR",
+    "lr_scheduler_gen_params": {
+        "gamma": 0.999875,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.999875,
+        "last_epoch": -1
+    },
+    "kl_loss_alpha": 1.0,
+    "disc_loss_alpha": 1.0,
+    "gen_loss_alpha": 1.0,
+    "feat_loss_alpha": 1.0,
+    "mel_loss_alpha": 45.0,
+    "return_wav": true,
+    "r": 1
+}

tts/tts_models--en--ljspeech--vits/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b71d7bea7bd4f6745b87a695174ec486f633ad6c4fecdcff7513d76d1fbafe6
+size 145588597