Update tiny models for BarkModel

config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "BarkModel"
+  ],
+  "coarse_acoustics_config": {
+    "bias": true,
+    "block_size": 256,
+    "bos_token_id": 32,
+    "dropout": 0.0,
+    "eos_token_id": 32,
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "input_vocab_size": 300,
+    "model_type": "coarse_acoustics",
+    "num_heads": 2,
+    "num_layers": 2,
+    "output_vocab_size": 300,
+    "pad_token_id": 32,
+    "use_cache": true
+  },
+  "codec_config": {
+    "audio_channels": 2,
+    "chunk_in_sec": null,
+    "chunk_length_s": null,
+    "codebook_dim": 32,
+    "codebook_size": 64,
+    "compress": 2,
+    "dilation_growth_rate": 2,
+    "hidden_size": 32,
+    "kernel_size": 7,
+    "last_kernel_size": 7,
+    "model_type": "encodec",
+    "norm_type": "weight_norm",
+    "normalize": false,
+    "num_filters": 8,
+    "num_lstm_layers": 1,
+    "num_residual_layers": 1,
+    "overlap": null,
+    "pad_mode": "reflect",
+    "residual_kernel_size": 3,
+    "sampling_rate": 24000,
+    "target_bandwidths": [
+      1.5,
+      3.0,
+      6.0,
+      12.0,
+      24.0
+    ],
+    "trim_right_ratio": 1.0,
+    "upsampling_ratios": [
+      8,
+      4
+    ],
+    "use_causal_conv": true,
+    "use_conv_shortcut": true
+  },
+  "dtype": "float32",
+  "fine_acoustics_config": {
+    "bias": true,
+    "block_size": 256,
+    "bos_token_id": 32,
+    "dropout": 0.0,
+    "eos_token_id": 32,
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "input_vocab_size": 300,
+    "model_type": "fine_acoustics",
+    "n_codes_given": 1,
+    "n_codes_total": 8,
+    "num_heads": 2,
+    "num_layers": 2,
+    "output_vocab_size": 300,
+    "pad_token_id": 32,
+    "tie_word_embeddings": true,
+    "use_cache": true
+  },
+  "initializer_range": 0.02,
+  "model_type": "bark",
+  "semantic_config": {
+    "bias": true,
+    "block_size": 256,
+    "bos_token_id": 32,
+    "dropout": 0.0,
+    "eos_token_id": 32,
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "input_vocab_size": 300,
+    "model_type": "semantic",
+    "num_heads": 2,
+    "num_layers": 2,
+    "output_vocab_size": 300,
+    "pad_token_id": 32,
+    "use_cache": true
+  },
+  "transformers_version": "5.16.0.dev0"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.16.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2e3ecd388a3bc2993c52fbc09704031e2ec2395afb439059b488b6fe4a52ca
+size 934372

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "processor_class": "BarkProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}