Automatic Speech Recognition
Transformers
Safetensors
VibeVoice
ASR
Transcription
Speech-to-Text
Streaming
Instructions to use microsoft/VibeVoice-ASR-Streaming-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/VibeVoice-ASR-Streaming-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="microsoft/VibeVoice-ASR-Streaming-7B")# Load model directly from transformers import AutoProcessor, VibeVoiceForASRStreamingTraining processor = AutoProcessor.from_pretrained("microsoft/VibeVoice-ASR-Streaming-7B") model = VibeVoiceForASRStreamingTraining.from_pretrained("microsoft/VibeVoice-ASR-Streaming-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from microsoft/VibeVoice-ASR-Streaming-7B: direct link, hf CLI and curl.
- Browser
- Download file 192 Bytes
-
https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://microsoft/VibeVoice-ASR-Streaming-7B/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B/resolve/main/preprocessor_config.json
192 Bytes
| { | |
| "speech_tok_compress_ratio": 3200, | |
| "target_sample_rate": 24000, | |
| "normalize_audio": false, | |
| "chunk_frames": 22, | |
| "lookahead_frames": 4, | |
| "processor_class": "VibeVoiceASRProcessor" | |
| } | |