Upload 9 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,247 @@
 ---
 license: mit
+language:
+- en
+- multilingual
+library_name: transformers
+tags:
+- text-to-speech
+- audio
+- tts
+- voice
+- quantized
+- 8bit
+- bitsandbytes
+- vibevoice
+pipeline_tag: text-to-audio
+model-index:
+- name: VibeVoice-Large-Q8
+  results: []
 ---
+
+# VibeVoice-Large-Q8 - Selective 8bit Quantization
+
+<div align="center">
+
+**The first 8-bit VibeVoice model that actually works**
+
+[![License](https://img.shields.io/badge/license-MIT-blue)](LICENSE)
+[![Model Size](https://img.shields.io/badge/size-11.6%20GB-green)](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8)
+[![Quality](https://img.shields.io/badge/audio-identical%20quality-brightgreen)](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8)
+
+[🤗 Model](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8) • [💻 ComfyUI](https://github.com/Enemyx-net/VibeVoice-ComfyUI) • [📖 Docs](https://github.com/Enemyx-net/VibeVoice-ComfyUI/blob/main/README.md)
+
+</div>
+
+---
+
+## 🎯 Why This Model is Different
+
+If you've tried other 8-bit quantized VibeVoice models, you probably got nothing but static noise. **This one actually works.**
+
+The secret? **Selective quantization**: I only quantized the language model (the most robust part), while keeping audio-critical components (diffusion head, VAE, connectors) at full precision.
+
+### Results
+- ✅ Perfect audio, identical to the original model
+- ✅ 11.6 GB instead of 18.7 GB (-38%)
+- ✅ Uses ~12 GB VRAM instead of 20 GB
+- ✅ Works on 12 GB GPUs (RTX 3060, 4070 Ti, etc.)
+
+---
+
+## 🚨 The Problem with Other 8-bit Models
+
+Most 8-bit models you'll find online quantize **everything** aggressively:
+**Result:** Audio components get quantized → numerical errors propagate → audio = pure noise.
+
+---
+
+## ✅ The Solution: Selective Quantization
+
+I only quantized what can be safely quantized without losing quality.
+
+**Result:** 52% of parameters quantized, 48% at full precision = perfect audio quality.
+
+---
+
+## 📊 Quick Comparison
+
+| Model | Size | Audio Quality | Status |
+|-------|------|---------------|--------|
+| Original VibeVoice | 18.7 GB | ⭐⭐⭐⭐⭐ | Full precision |
+| Other 8-bit models | 10.6 GB | 💥 NOISE | ❌ Don't work |
+| **This model** | **11.6 GB** | ⭐⭐⭐⭐⭐ | ✅ **Perfect** |
+
++1.0 GB vs other 8-bit models = perfect audio instead of noise. Worth it.
+
+---
+
+## 💻 How to Use It
+
+### With Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoProcessor
+import torch
+import scipy.io.wavfile as wavfile
+
+# Load model
+model = AutoModelForCausalLM.from_pretrained(
+    "FabioSarracino/VibeVoice-Large-Q8",
+    device_map="auto",
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+)
+
+processor = AutoProcessor.from_pretrained(
+    "FabioSarracino/VibeVoice-Large-Q8",
+    trust_remote_code=True
+)
+
+# Generate audio
+text = "Hello, this is VibeVoice speaking."
+inputs = processor(text, return_tensors="pt").to(model.device)
+output = model.generate(**inputs, max_new_tokens=None)
+
+# Save
+audio = output.speech_outputs[0].cpu().numpy()
+wavfile.write("output.wav", 24000, audio)
+```
+
+### With ComfyUI (recommended)
+
+1. Install the custom node:
+   ```bash
+   cd ComfyUI/custom_nodes
+   git clone https://github.com/Enemyx-net/VibeVoice-ComfyUI
+   ```
+
+2. Download this model to `ComfyUI/models/vibevoice/`
+
+3. Restart ComfyUI and use it normally!
+
+---
+
+## 💾 System Requirements
+
+### Minimum
+- **VRAM:** 12 GB
+- **RAM:** 16 GB
+- **GPU:** NVIDIA with CUDA (required)
+- **Storage:** 11 GB
+
+### Recommended
+- **VRAM:** 16+ GB
+- **RAM:** 32 GB
+- **GPU:** RTX 3090/4090, A5000 or better
+
+⚠️ **Not supported:** CPU, Apple Silicon (MPS), AMD GPUs
+
+---
+
+## ⚠️ Limitations
+
+1. **Requires NVIDIA GPU with CUDA** - won't work on CPU or Apple Silicon
+2. **Inference only** - don't use for fine-tuning
+3. **Requires:**
+   - `transformers>=4.51.3`
+   - `bitsandbytes>=0.43.0`
+
+---
+
+## 🆚 When to Use This Model
+
+### ✅ Use this 8-bit if:
+- You have 12-16 GB VRAM
+- You want maximum quality with reduced size
+- You need a production-ready model
+- You want the best size/quality balance
+
+### Use full precision (18.7 GB) if:
+- You have unlimited VRAM (24+ GB)
+- You're doing research requiring absolute precision
+
+### Use 4-bit NF4 (~6.6 GB) if:
+- You only have 8-10 GB VRAM
+- You can accept a small quality trade-off
+
+---
+
+## 🔧 Troubleshooting
+
+### "OutOfMemoryError" during loading
+
+- Close other GPU applications
+- Use `device_map="auto"`
+- Reduce batch size to 1
+
+### "BitsAndBytes not found"
+
+```bash
+pip install bitsandbytes>=0.43.0
+```
+
+### Audio sounds distorted
+
+This shouldn't happen! If it does:
+1. Verify you downloaded the correct model
+2. Update transformers: `pip install --upgrade transformers`
+3. Check CUDA: `torch.cuda.is_available()` should return `True`
+
+---
+
+## 📚 Citation
+
+```bibtex
+@misc{vibevoice-q8-2025,
+  title={VibeVoice-Large-Q8: Selective 8-bit Quantization for Audio Quality},
+  author={Fabio Sarracino},
+  year={2025},
+  url={https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8}
+}
+```
+
+### Original Model
+
+```bibtex
+@misc{vibevoice2024,
+  title={VibeVoice: High-Quality Text-to-Speech with Large Language Models},
+  author={Microsoft Research},
+  year={2024},
+  url={https://github.com/microsoft/VibeVoice}
+}
+```
+
+---
+
+## 🔗 Related Resources
+
+- [Original Model](https://huggingface.co/aoi-ot/VibeVoice-Large) - Full precision base
+- [ComfyUI Node](https://github.com/Enemyx-net/VibeVoice-ComfyUI) - ComfyUI integration
+
+---
+
+## 📜 License
+
+MIT License.
+
+---
+
+## 🤝 Support
+
+- **Issues:** [GitHub Issues](https://github.com/Enemyx-net/VibeVoice-ComfyUI/issues)
+- **Questions:** [HuggingFace Discussions](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8/discussions)
+
+If this model helped you, leave a ⭐ on GitHub!
+
+---
+
+<div align="center">
+
+**Created by [Fabio Sarracino](https://github.com/Enemyx-net)**
+
+*The first 8-bit VibeVoice model that actually works*
+
+[🤗 HuggingFace](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8) • [💻 GitHub](https://github.com/Enemyx-net/VibeVoice-ComfyUI)
+
+</div>

config.json

@@ -0,0 +1,151 @@
+{
+  "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",
+    "torch_dtype": "bfloat16",
+    "vae_dim": 64,
+    "weight_init_value": 0.01
+  },
+  "acoustic_vae_dim": 64,
+  "architectures": [
+    "VibeVoiceForConditionalGenerationInference"
+  ],
+  "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,
+    "torch_dtype": "bfloat16"
+  },
+  "hidden_size": 3584,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "model_type": "vibevoice",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "quant_method": "bitsandbytes",
+    "_load_in_8bit": true,
+    "_load_in_4bit": false,
+    "load_in_8bit": true,
+    "load_in_4bit": false,
+    "llm_int8_threshold": 3.0,
+    "llm_int8_skip_modules": [
+      "prediction_head",
+      "acoustic_connector",
+      "semantic_connector",
+      "acoustic_tokenizer",
+      "semantic_tokenizer"
+    ],
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "bnb_8bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8"
+  },
+  "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",
+    "torch_dtype": "bfloat16",
+    "vae_dim": 128,
+    "weight_init_value": 0.01
+  },
+  "semantic_vae_dim": 128,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "vocab_size": 152064,
+  "_quantization_method": "bitsandbytes",
+  "_quantization_variant": "A"
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f98075dac463766219e6e61ff5fe9ab969f8fea621a65906f1d6793f2eaf72
+size 4987685394

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b79643eec675f7173a1b61040af9c4708b257005ae4175a64129d47cc8b4944
+size 4958656224

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293e0b5f0577756d67bc273142145a2a490be7909ab55f5b3dfb2f4f0993669e
+size 1676460817

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"
+}