Upload VibeVoice 1.5B model

README.md

@@ -2,7 +2,7 @@
 license: mit
 ---
 
-## Model description
+## VibeVoice: A Frontier Open-Source Text-to-Speech Model
 
 VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking.
 
@@ -10,6 +10,11 @@ A core innovation of VibeVoice is its use of continuous speech tokenizers (Acous
 
 The model can synthesize speech up to **90 minutes** long with up to **4 distinct speakers**, surpassing the typical 1-2 speaker limits of many prior models. 
 
+
+➡️ **Project Demo:** [microsoft/VibeVoice-Demo](https://microsoft.github.io/VibeVoice)
+
+➡️ **Github Code:** [microsoft/VibeVoice-Code](https://github.com/microsoft/VibeVoice)
+
 ## Training details
 Transformer-based Large Language Model (LLM) integrated with specialized acoustic and semantic tokenizers and a diffusion-based decoding head.
 - LLM: [Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) for this release.

config.json

@@ -0,0 +1,115 @@
+{
+  "acoustic_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": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "max_position_embeddings": 65536,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+  },
+  "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": 1536,
+    "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f0a61ddeaeb028e3af540ba4dee7933ad30f9f30b6e1320dd9c875a2daa033
+size 1975317828

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c3891f7b2493eb48a9eb6f5be0df48d4f1a4bfd952d84e21683ca6d0bf7969
+size 1983051688

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6e7e5e86b4a41fffbe1f3aaf445d0d50b5e21ed47574101b777f77d75fa196
+size 1449832938

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/Qwen2.5-1.5B"
+}