Instructions to use onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration") model = AutoModelForMultimodalLM.from_pretrained("onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration: direct link, hf CLI and curl.
- Browser
- Download file 335 Bytes
-
https://huggingface.co/onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/onnx-internal-testing/tiny-random-VoxtralRealtimeForConditionalGeneration/resolve/main/preprocessor_config.json
335 Bytes
| { | |
| "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" | |
| } | |