Upload model

config.json

@@ -1,166 +1,344 @@
 {
+  "_commit_hash": null,
+  "_name_or_path": "/home/yoach/bark_weigths/model/",
+  "architectures": [
+    "BarkModel"
+  ],
   "coarse_acoustics_config": {
-    "_from_model_config": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "BarkCoarseModel"
+    ],
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
+    "bias": false,
+    "block_size": 1024,
     "bos_token_id": null,
-    "coarse_infer_token": 12050,
-    "coarse_rate_hz": 75,
-    "coarse_semantic_pad_token": 12048,
-    "constraints": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
-    "do_sample": true,
+    "do_sample": false,
+    "dropout": 0.0,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
-    "encoder_repetition_penalty": 1.0,
     "eos_token_id": null,
-    "epsilon_cutoff": 0.0,
-    "eta_cutoff": 0.0,
     "exponential_decay_length_penalty": null,
-    "force_words_ids": null,
+    "finetuning_task": null,
     "forced_bos_token_id": null,
-    "forced_decoder_ids": null,
     "forced_eos_token_id": null,
-    "generation_kwargs": {},
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "input_vocab_size": 12096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
     "length_penalty": 1.0,
-    "max_coarse_history": 630,
-    "max_coarse_input_length": 256,
     "max_length": 20,
-    "max_new_tokens": null,
-    "max_time": null,
     "min_length": 0,
-    "min_new_tokens": null,
-    "n_coarse_codebooks": 2,
+    "model_type": "coarse_acoustics",
+    "n_codes_given": 1,
+    "n_codes_total": 8,
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
+    "num_heads": 16,
+    "num_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
+    "output_vocab_size": 12096,
     "pad_token_id": null,
-    "penalty_alpha": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
     "remove_invalid_values": false,
-    "renormalize_logits": true,
     "repetition_penalty": 1.0,
+    "return_dict": true,
     "return_dict_in_generate": false,
-    "sliding_window_len": 60,
+    "sep_token_id": null,
     "suppress_tokens": null,
-    "temperature": 0.7,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
     "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
+    "use_bfloat16": false,
     "use_cache": true
   },
-  "codebook_size": 1024,
+  "codec_config": {
+    "_name_or_path": "ArthurZ/encodec_24khz",
+    "add_cross_attention": false,
+    "architectures": [
+      "EncodecModel"
+    ],
+    "audio_channels": 1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_length_s": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_dim": 128,
+    "codebook_size": 1024,
+    "compress": 2,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dilation_growth_rate": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 128,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "kernel_size": 7,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "last_kernel_size": 7,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "encodec",
+    "no_repeat_ngram_size": 0,
+    "norm_type": "weight_norm",
+    "normalize": false,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_filters": 32,
+    "num_lstm_layers": 2,
+    "num_residual_layers": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "overlap": null,
+    "pad_mode": "reflect",
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "residual_kernel_size": 3,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 24000,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "target_bandwidths": [
+      1.5,
+      3.0,
+      6.0,
+      12.0,
+      24.0
+    ],
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.31.0.dev0",
+    "trim_right_ratio": 1.0,
+    "typical_p": 1.0,
+    "upsampling_ratios": [
+      8,
+      5,
+      4,
+      2
+    ],
+    "use_bfloat16": false,
+    "use_causal_conv": true
+  },
   "fine_acoustics_config": {
-    "_from_model_config": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "BarkFineModel"
+    ],
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
+    "bias": false,
+    "block_size": 1024,
     "bos_token_id": null,
-    "constraints": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
+    "dropout": 0.0,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
-    "encoder_repetition_penalty": 1.0,
     "eos_token_id": null,
-    "epsilon_cutoff": 0.0,
-    "eta_cutoff": 0.0,
     "exponential_decay_length_penalty": null,
-    "force_words_ids": null,
+    "finetuning_task": null,
     "forced_bos_token_id": null,
-    "forced_decoder_ids": null,
     "forced_eos_token_id": null,
-    "generation_kwargs": {},
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "input_vocab_size": 1056,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
     "length_penalty": 1.0,
-    "max_fine_history_length": 512,
-    "max_fine_input_length": 1024,
     "max_length": 20,
-    "max_new_tokens": null,
-    "max_time": null,
     "min_length": 0,
-    "min_new_tokens": null,
-    "n_fine_codebooks": 8,
+    "model_type": "fine_acoustics",
+    "n_codes_given": 1,
+    "n_codes_total": 8,
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
+    "num_heads": 16,
+    "num_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
+    "output_vocab_size": 1056,
     "pad_token_id": null,
-    "penalty_alpha": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
     "remove_invalid_values": false,
-    "renormalize_logits": false,
     "repetition_penalty": 1.0,
+    "return_dict": true,
     "return_dict_in_generate": false,
+    "sep_token_id": null,
     "suppress_tokens": null,
-    "temperature": 0.5,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
     "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
+    "use_bfloat16": false,
     "use_cache": true
   },
+  "initializer_range": 0.02,
   "model_type": "bark",
-  "sample_rate": 24000,
   "semantic_config": {
-    "_from_model_config": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "BarkSemanticModel"
+    ],
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
+    "bias": false,
+    "block_size": 1024,
     "bos_token_id": null,
-    "constraints": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
-    "do_sample": true,
+    "do_sample": false,
+    "dropout": 0.0,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
-    "encoder_repetition_penalty": 1.0,
-    "eos_token_id": 10000,
-    "epsilon_cutoff": 0.0,
-    "eta_cutoff": 0.0,
+    "eos_token_id": null,
     "exponential_decay_length_penalty": null,
-    "force_words_ids": null,
+    "finetuning_task": null,
     "forced_bos_token_id": null,
-    "forced_decoder_ids": null,
     "forced_eos_token_id": null,
-    "generation_kwargs": {},
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "input_vocab_size": 129600,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
     "length_penalty": 1.0,
-    "max_input_semantic_length": 256,
     "max_length": 20,
-    "max_new_tokens": 768,
-    "max_time": null,
     "min_length": 0,
-    "min_new_tokens": null,
+    "model_type": "semantic",
+    "n_codes_given": 1,
+    "n_codes_total": 8,
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
+    "num_heads": 16,
+    "num_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
+    "output_vocab_size": 10048,
     "pad_token_id": null,
-    "penalty_alpha": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
     "remove_invalid_values": false,
-    "renormalize_logits": true,
     "repetition_penalty": 1.0,
+    "return_dict": true,
     "return_dict_in_generate": false,
-    "semantic_infer_token": 129599,
-    "semantic_pad_token": 10000,
-    "semantic_rate_hz": 49.9,
-    "semantic_vocab_size": 10000,
+    "sep_token_id": null,
     "suppress_tokens": null,
-    "temperature": 0.7,
-    "text_encoding_offset": 10048,
-    "text_pad_token": 129595,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
     "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
+    "use_bfloat16": false,
     "use_cache": true
-  }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null
 }

generation_config.json

@@ -162,5 +162,6 @@
     "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
     "use_cache": true
-  }
+  },
+  "transformers_version": "4.31.0.dev0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be95e5fee92f8134ed67ae5eb418f202af5d005a5a617ffeacf82b9326a7cd4e
-size 4486642261
+oid sha256:d9ac007f13624882c82d561378eb356321594eabf320fdbbe32c25b098dad4df
+size 4516921809