Upload folder using huggingface_hub

tts_models--multilingual--multi-dataset--bark/coarse_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286abc253d4d7f4d148325df07585f7ca4fca36ce40577a1ddd744a8b35e4388
+size 3934534533

tts_models--multilingual--multi-dataset--bark/config.json

@@ -0,0 +1,205 @@
+{
+	"model": "bark",
+    "output_path": "output",
+    "logger_uri": null,
+    "run_name": "run",
+    "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": 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": 0,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": 0.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "radam",
+    "optimizer_params": null,
+    "lr_scheduler": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "num_loader_workers": 0,
+    "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": 45,
+        "do_rms_norm": false,
+        "db_level": null,
+        "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,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 1.0,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": false,
+    "text_cleaner": null,
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": null,
+    "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_energy": false,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "",
+            "meta_file_train": "",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [],
+    "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,
+    "num_chars": 0,
+    "semantic_config": {
+        "block_size": 1024,
+        "input_vocab_size": 10048,
+        "output_vocab_size": 10048,
+        "n_layer": 12,
+        "n_head": 12,
+        "n_embd": 768,
+        "dropout": 0.0,
+        "bias": true
+    },
+    "fine_config": {
+        "block_size": 1024,
+        "input_vocab_size": 10048,
+        "output_vocab_size": 10048,
+        "n_layer": 12,
+        "n_head": 12,
+        "n_embd": 768,
+        "dropout": 0.0,
+        "bias": true,
+        "n_codes_total": 8,
+        "n_codes_given": 1
+    },
+    "coarse_config": {
+        "block_size": 1024,
+        "input_vocab_size": 10048,
+        "output_vocab_size": 10048,
+        "n_layer": 12,
+        "n_head": 12,
+        "n_embd": 768,
+        "dropout": 0.0,
+        "bias": true
+    },
+    "CONTEXT_WINDOW_SIZE": 1024,
+    "SEMANTIC_RATE_HZ": 49.9,
+    "SEMANTIC_VOCAB_SIZE": 10000,
+    "CODEBOOK_SIZE": 1024,
+    "N_COARSE_CODEBOOKS": 2,
+    "N_FINE_CODEBOOKS": 8,
+    "COARSE_RATE_HZ": 75,
+    "SAMPLE_RATE": 24000,
+    "USE_SMALLER_MODELS": false,
+    "TEXT_ENCODING_OFFSET": 10048,
+    "SEMANTIC_PAD_TOKEN": 10000,
+    "TEXT_PAD_TOKEN": 129595,
+    "SEMANTIC_INFER_TOKEN": 129599,
+    "COARSE_SEMANTIC_PAD_TOKEN": 12048,
+    "COARSE_INFER_TOKEN": 12050,
+    "REMOTE_MODEL_PATHS": {
+        "text": {
+            "path": "https://huggingface.co/erogol/bark/tree/main/text_2.pt",
+            "checksum": "54afa89d65e318d4f5f80e8e8799026a"
+        },
+        "coarse": {
+            "path": "https://huggingface.co/erogol/bark/tree/main/coarse_2.pt",
+            "checksum": "8a98094e5e3a255a5c9c0ab7efe8fd28"
+        },
+        "fine": {
+            "path": "https://huggingface.co/erogol/bark/tree/main/fine_2.pt",
+            "checksum": "59d184ed44e3650774a2f0503a48a97b"
+        }
+    },
+    "LOCAL_MODEL_PATHS": {
+        "text": "/root/.local/share/tts/suno/bark_v0/text_2.pt",
+        "coarse": "/root/.local/share/tts/suno/bark_v0/coarse_2.pt",
+        "fine": "/root/.local/share/tts/suno/bark_v0/fine_2.pt",
+        "hubert_tokenizer": "/root/.local/share/tts/suno/bark_v0/tokenizer.pth",
+        "hubert": "/root/.local/share/tts/suno/bark_v0/hubert.pt"
+    },
+    "SMALL_REMOTE_MODEL_PATHS": {
+        "text": {
+            "path": "https://huggingface.co/erogol/bark/tree/main/text.pt"
+        },
+        "coarse": {
+            "path": "https://huggingface.co/erogol/bark/tree/main/coarse.pt"
+        },
+        "fine": {
+            "path": "https://huggingface.co/erogol/bark/tree/main/fine.pt"
+        }
+    },
+    "CACHE_DIR": "/root/.local/share/tts/suno/bark_v0"
+}

tts_models--multilingual--multi-dataset--bark/fine_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799c87afab4b01537094c63ea231f2c42c9c07aeb16773690540ad251a6d8fab
+size 3741740229

tts_models--multilingual--multi-dataset--bark/hubert.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1703cf8d2cdc76f8c046f5f6a9bcd224e0e6caf4744cad1a1f4199c32cac8c8d
+size 1136468879

tts_models--multilingual--multi-dataset--bark/text_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0019dfc4b32d63c1392aa264aed2253c1e0c2fb09216f8e2cc269bbfb8bb49b5
+size 9

tts_models--multilingual--multi-dataset--bark/tokenizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf7eeab58835c5fc1cfbd3fd19c457fbd07859a5f036a6bfea4b6840716c1e7
+size 103981977

tts_models--multilingual--multi-dataset--xtts/config.json

@@ -0,0 +1,159 @@
+{
+    "output_path": "output",
+    "logger_uri": null,
+    "run_name": "run",
+    "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",
+    "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": null,
+    "print_eval": false,
+    "test_delay_epochs": 0,
+    "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": 0.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "radam",
+    "optimizer_params": null,
+    "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": "xtts",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "sample_rate": 22050,
+        "output_sample_rate": 24000
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": false,
+    "text_cleaner": null,
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": null,
+    "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_energy": false,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "",
+            "meta_file_train": "",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [],
+    "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,
+    "model_args": {
+        "gpt_batch_size": 1,
+        "enable_redaction": false,
+        "kv_cache": true,
+        "gpt_checkpoint": null,
+        "clvp_checkpoint": null,
+        "decoder_checkpoint": null,
+        "num_chars": 255,
+        "tokenizer_file": "",
+        "gpt_max_audio_tokens": 605,
+        "gpt_max_text_tokens": 402,
+        "gpt_max_prompt_tokens": 70,
+        "gpt_layers": 30,
+        "gpt_n_model_channels": 1024,
+        "gpt_n_heads": 16,
+        "gpt_number_text_tokens": 6681,
+        "gpt_start_text_token": null,
+        "gpt_stop_text_token": null,
+        "gpt_num_audio_tokens": 1026,
+        "gpt_start_audio_token": 1024,
+        "gpt_stop_audio_token": 1025,
+        "gpt_code_stride_len": 1024,
+        "gpt_use_masking_gt_prompt_approach": true,
+        "gpt_use_perceiver_resampler": true,
+        "input_sample_rate": 22050,
+        "output_sample_rate": 24000,
+        "output_hop_length": 256,
+        "decoder_input_dim": 1024,
+        "d_vector_dim": 512,
+        "cond_d_vector_in_each_upsampling_layer": true,
+        "duration_const": 102400
+    },
+    "model_dir": null,
+    "languages": [
+        "en",
+        "es",
+        "fr",
+        "de",
+        "it",
+        "pt",
+        "pl",
+        "tr",
+        "ru",
+        "nl",
+        "cs",
+        "ar",
+        "zh-cn",
+        "hu",
+        "ko",
+        "ja",
+        "hi"
+    ],
+    "temperature": 0.75,
+    "length_penalty": 1.0,
+    "repetition_penalty": 5.0,
+    "top_k": 50,
+    "top_p": 0.85,
+    "num_gpt_outputs": 1,
+    "gpt_cond_len": 30,
+    "gpt_cond_chunk_len": 4,
+    "max_ref_len": 30,
+    "sound_norm_refs": false
+}

tts_models--multilingual--multi-dataset--xtts/hash.md5

@@ -0,0 +1 @@
+10f92b55c512af7a8d39d650547a15a7

tts_models--multilingual--multi-dataset--xtts/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ea20001c6a0a841c77e252d8409f6a74fb423e79b3206a0771ba5989776187
+size 1867929118

tts_models--multilingual--multi-dataset--xtts/speakers_xtts.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
+size 7754818