TTS model trained on Coqui TTS (Tacotron2 DDC).

scale_stats.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13474283738326a4c01132b4c347e35910f08cdff8b1c595b52fc238c94bdb4d
+size 10791

tts-config.json

@@ -0,0 +1,217 @@
+{
+    "output_path": "/ssd/___tts/thorsten-ddc/output",
+    "logger_uri": null,
+    "run_name": "Thorsten-Dec2021-22k-DDC",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "log_model_step": null,
+    "save_step": 2000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": true,
+    "save_best_after": 10000,
+    "target_loss": null,
+    "print_eval": true,
+    "test_delay_epochs": -1,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "epochs": 1000,
+    "batch_size": 64,
+    "eval_batch_size": 16,
+    "grad_clip": 5.0,
+    "scheduler_after_epoch": false,
+    "lr": 0.0001,
+    "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": false,
+    "training_seed": 54321,
+    "model": "tacotron2",
+    "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": 50.0,
+        "mel_fmax": null,
+        "spec_gain": 1.0,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 0.0,
+        "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": "de",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "basic_german_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/ssd/___tts/thorsten-ddc/output/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": true,
+    "sort_by_audio_len": false,
+    "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": [
+        {
+            "name": "ljspeech",
+            "path": "/ssd/___tts/datasets/Thorsten-Neutral-Dec2021-22k/",
+            "meta_file_train": "metadata_train.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "metadata_test.csv",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        "und \u00fcberzeugen dank feingef\u00fchl f\u00fcr den ganz gro\u00dfen leinwand-stoff.",
+        "zur schadensh\u00f6he gab es keine angaben.",
+        "au\u00dferdem k\u00f6nnen glasscheiben, w\u00e4nde und andere hindernisse das ergebnis beeinflussen.",
+        "ihre lippen m\u00fcssen dennoch nicht zwingend auf farbe verzichten.",
+        "es dauert lange, eine eigene Stimme zu entwickeln, aber jetzt wo ich sie habe, bin ich nie wieder still.",
+        "heute scheint die Sonne, Regen ist nicht zu erwarten.",
+        "die aktuelle Au\u00dfentemperatur betr\u00e4gt zw\u00f6lf Grad Celsius bei einer Luftfeuchtigkeit von achtunddrei\u00dfig Prozent."
+    ],
+    "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": null,
+    "gst_style_input": null,
+    "use_capacitron_vae": false,
+    "capacitron_vae": null,
+    "num_speakers": 1,
+    "num_chars": 131,
+    "r": 6,
+    "gradual_training": [
+        [
+            0,
+            6,
+            64
+        ],
+        [
+            10000,
+            4,
+            32
+        ],
+        [
+            50000,
+            3,
+            32
+        ],
+        [
+            100000,
+            2,
+            32
+        ]
+    ],
+    "memory_size": -1,
+    "prenet_type": "original",
+    "prenet_dropout": true,
+    "prenet_dropout_at_inference": false,
+    "stopnet": true,
+    "separate_stopnet": true,
+    "stopnet_pos_weight": 10.0,
+    "max_decoder_steps": 500,
+    "encoder_in_features": 512,
+    "decoder_in_features": 512,
+    "decoder_output_dim": 80,
+    "out_channels": 80,
+    "attention_type": "original",
+    "attention_heads": null,
+    "attention_norm": "sigmoid",
+    "attention_win": false,
+    "windowing": false,
+    "use_forward_attn": false,
+    "forward_attn_mask": false,
+    "transition_agent": false,
+    "location_attn": true,
+    "bidirectional_decoder": false,
+    "double_decoder_consistency": true,
+    "ddc_r": 6,
+    "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": 0.25,
+    "decoder_diff_spec_alpha": 0.25,
+    "decoder_ssim_alpha": 0.25,
+    "postnet_ssim_alpha": 0.25,
+    "ga_alpha": 5.0,
+    "github_branch": "* main"
+}

tts-model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1ce9b284491421e2054509beecb74d1bae53c67d1befeed5b2bbd990e89bb8
+size 572143679

vocoder-config.json

@@ -0,0 +1,189 @@
+{
+    "output_path": "/home/ubuntu/output-hifigan",
+    "logger_uri": null,
+    "run_name": "Thorsten-Neutral-Dec2021-22k-HifiGAN",
+    "project_name": null,
+    "run_description": "HifiGAN vocoder model for Thorsten Neutral Dec2021 22k Samplerate Tacotron2 DDC model",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": "loss_0",
+    "print_eval": false,
+    "test_delay_epochs": 5,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": null,
+    "scheduler_after_epoch": true,
+    "lr": 0.0001,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "weight_decay": 0.0
+    },
+    "lr_scheduler": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "hifigan",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 4,
+    "use_noise_augment": true,
+    "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": null,
+        "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": "/Users/thorsten/Library/Application Support/tts/vocoder_models--de--thorsten--hifigan_v1/scale_stats.npy"
+    },
+    "eval_split_size": 10,
+    "data_path": "/home/ubuntu/Thorsten-Voice-Neutral-Dec2021-22kHz",
+    "feature_path": "/home/ubuntu/features_330k",
+    "seq_len": 8192,
+    "pad_short": 2000,
+    "conv_pad": 0,
+    "use_cache": false,
+    "wd": 1e-06,
+    "use_stft_loss": false,
+    "use_subband_stft_loss": false,
+    "use_mse_gan_loss": true,
+    "use_hinge_gan_loss": false,
+    "use_feat_match_loss": true,
+    "use_l1_spec_loss": true,
+    "stft_loss_weight": 0.0,
+    "subband_stft_loss_weight": 0.0,
+    "mse_G_loss_weight": 1.0,
+    "hinge_G_loss_weight": 0.0,
+    "feat_match_loss_weight": 108.0,
+    "l1_spec_loss_weight": 45.0,
+    "stft_loss_params": {
+        "n_ffts": [
+            1024,
+            2048,
+            512
+        ],
+        "hop_lengths": [
+            120,
+            240,
+            50
+        ],
+        "win_lengths": [
+            600,
+            1200,
+            240
+        ]
+    },
+    "l1_spec_loss_params": {
+        "use_mel": true,
+        "sample_rate": 22050,
+        "n_fft": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mels": 80,
+        "mel_fmin": 50.0,
+        "mel_fmax": null
+    },
+    "lr_gen": 0.0001,
+    "lr_disc": 0.0001,
+    "lr_scheduler_gen": "ExponentialLR",
+    "lr_scheduler_gen_params": {
+        "gamma": 0.999,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.999,
+        "last_epoch": -1
+    },
+    "use_pqmf": false,
+    "diff_samples_for_G_and_D": false,
+    "discriminator_model": "hifigan_discriminator",
+    "generator_model": "hifigan_generator",
+    "generator_model_params": {
+        "upsample_factors": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "upsample_initial_channel": 512,
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "resblock_type": "1"
+    }
+}

vocoder-model_file.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c503e5553714b4fd176c3acaed1b8956815078e9521a4a782dd340952f32ce5f
+size 1016383933