Automatic Speech Recognition
Safetensors
VibeVoice
vibevoice.c
speculative-decoding
dflash
awq
compressed-tensors
speech-recognition
4-bit precision
Instructions to use Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VibeVoice
How to use Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2 with VibeVoice:
import torch, soundfile as sf, librosa, numpy as np from vibevoice.processor.vibevoice_processor import VibeVoiceProcessor from vibevoice.modular.modeling_vibevoice_inference import VibeVoiceForConditionalGenerationInference # Load voice sample (should be 24kHz mono) voice, sr = sf.read("path/to/voice_sample.wav") if voice.ndim > 1: voice = voice.mean(axis=1) if sr != 24000: voice = librosa.resample(voice, sr, 24000) processor = VibeVoiceProcessor.from_pretrained("Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2", torch_dtype=torch.bfloat16 ).to("cuda").eval() model.set_ddpm_inference_steps(5) inputs = processor(text=["Speaker 0: Hello!\nSpeaker 1: Hi there!"], voice_samples=[[voice]], return_tensors="pt") audio = model.generate(**inputs, cfg_scale=1.3, tokenizer=processor.tokenizer).speech_outputs[0] sf.write("output.wav", audio.cpu().numpy().squeeze(), 24000) - Notebooks
- Google Colab
- Kaggle
Download quantization_environment.json from Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2: direct link, hf CLI and curl.
- Browser
- Download file 194 Bytes
-
https://huggingface.co/Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2/resolve/463a3ca66fc35a20043753f92984fc66f858926a/quantization_environment.json
- Command line
-
hf download hf://Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2@463a3ca66fc35a20043753f92984fc66f858926a/quantization_environment.json
-
curl -L -o quantization_environment.json https://huggingface.co/Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2/resolve/463a3ca66fc35a20043753f92984fc66f858926a/quantization_environment.json
194 Bytes
| { | |
| "torch": "2.13.0", | |
| "transformers": "5.14.1", | |
| "llmcompressor": "0.13.0", | |
| "compressed-tensors": "0.18.0", | |
| "datasets": "5.0.1", | |
| "safetensors": "0.8.0", | |
| "huggingface-hub": "1.32.0" | |
| } |