Upload folder using huggingface_hub

config.json

@@ -0,0 +1,116 @@
+{
+  "acostic_vae_dim": 64,
+  "acoustic_tokenizer_config": {
+    "causal": true,
+    "channels": 1,
+    "conv_bias": true,
+    "conv_norm": "none",
+    "corpus_normalize": 0.0,
+    "decoder_depths": null,
+    "decoder_n_filters": 32,
+    "decoder_ratios": [
+      8,
+      5,
+      5,
+      4,
+      2,
+      2
+    ],
+    "disable_last_norm": true,
+    "encoder_depths": "3-3-3-3-3-3-8",
+    "encoder_n_filters": 32,
+    "encoder_ratios": [
+      8,
+      5,
+      5,
+      4,
+      2,
+      2
+    ],
+    "fix_std": 0.5,
+    "layer_scale_init_value": 1e-06,
+    "layernorm": "RMSNorm",
+    "layernorm_elementwise_affine": true,
+    "layernorm_eps": 1e-05,
+    "mixer_layer": "depthwise_conv",
+    "model_type": "vibevoice_acoustic_tokenizer",
+    "pad_mode": "constant",
+    "std_dist_type": "gaussian",
+    "vae_dim": 64,
+    "weight_init_value": 0.01
+  },
+  "architectures": [
+    "VibeVoiceForConditionalGeneration"
+  ],
+  "decoder_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_mrope": false,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+  },
+  "diffusion_head_config": {
+    "ddpm_batch_mul": 4,
+    "ddpm_beta_schedule": "cosine",
+    "ddpm_num_inference_steps": 20,
+    "ddpm_num_steps": 1000,
+    "diffusion_type": "ddpm",
+    "head_ffn_ratio": 3.0,
+    "head_layers": 4,
+    "hidden_size": 3584,
+    "latent_size": 64,
+    "model_type": "vibevoice_diffusion_head",
+    "prediction_type": "v_prediction",
+    "rms_norm_eps": 1e-05,
+    "speech_vae_dim": 64
+  },
+  "model_type": "vibevoice",
+  "semantic_tokenizer_config": {
+    "causal": true,
+    "channels": 1,
+    "conv_bias": true,
+    "conv_norm": "none",
+    "corpus_normalize": 0.0,
+    "disable_last_norm": true,
+    "encoder_depths": "3-3-3-3-3-3-8",
+    "encoder_n_filters": 32,
+    "encoder_ratios": [
+      8,
+      5,
+      5,
+      4,
+      2,
+      2
+    ],
+    "fix_std": 0,
+    "layer_scale_init_value": 1e-06,
+    "layernorm": "RMSNorm",
+    "layernorm_elementwise_affine": true,
+    "layernorm_eps": 1e-05,
+    "mixer_layer": "depthwise_conv",
+    "model_type": "vibevoice_semantic_tokenizer",
+    "pad_mode": "constant",
+    "std_dist_type": "none",
+    "vae_dim": 128,
+    "weight_init_value": 0.01
+  },
+  "semantic_vae_dim": 128,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae28d5c8f3587b518c7e371e96ebb69f74d854a854119acf433952bbc1926325
+size 1886424044

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56b1ca707e31e435ded8b03baa4938d88275bf0ba7033935a16d8173a99ff85
+size 1864468520

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48bfb4af453d45e488050e90d3f39da0189f1c10a77d75223c2c2ced8b035baa
+size 1864468520

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4893be477be68e53b8a9616422b99065f3d1431cce9efe0a1653495e9cf4df6
+size 1864468544

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:471690e9846e791def400fefa3d2103c9839dc8a3e987b175f6539c7412422d6
+size 1864468568

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7918d400ba895b15a1126fde242028e5d05b37bab0c0427944de81df80f901f
+size 1864468568

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f00ebea5a9f76eea891b3457621955433149ae603d921afa1498e46683ba37
+size 1864468568

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4b6fce97b76e847c742b59ab9463fd04b6d9fa69fc33e747ff722c2ab8cc28
+size 1972552744

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824db8970518950117f0d6ed859740d973b9436718c24f29bc78854c4587a4b2
+size 1959739938

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc76bba7a46a0a748cc169efb6ccfb7617881e0fc3b533f67887d5957e1836e3
+size 1681341960

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "processor_class": "VibeVoiceProcessor",
+  "speech_tok_compress_ratio": 3200,
+  "db_normalize": true,
+  "audio_processor": {
+    "feature_extractor_type": "VibeVoiceTokenizerProcessor",
+    "sampling_rate": 24000,
+    "normalize_audio": true,
+    "target_dB_FS": -25,
+    "eps": 1e-06
+  },
+  "language_model_pretrained_name": "Qwen/Qwen2.5-7B"
+}