Automatic Speech Recognition
Transformers
Safetensors
voxtral_realtime
mistral
voxtral
voxtral-realtime
asr
quantization
bitsandbytes
int4
nf4
4-bit precision
Instructions to use meghanamakkapati/MistralAI_INT4_quantization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use meghanamakkapati/MistralAI_INT4_quantization with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="meghanamakkapati/MistralAI_INT4_quantization")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("meghanamakkapati/MistralAI_INT4_quantization") model = AutoModelForMultimodalLM.from_pretrained("meghanamakkapati/MistralAI_INT4_quantization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "feature_extractor": { | |
| "feature_extractor_type": "VoxtralRealtimeFeatureExtractor", | |
| "feature_size": 128, | |
| "global_log_mel_max": 1.5, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400 | |
| }, | |
| "processor_class": "VoxtralRealtimeProcessor" | |
| } | |