Model: OpenAI/whisper-tiny
Format: ONNX
Quantization: INT8
ExecutionProvider: CPU
Usage:
model_path = hf_hub_download(repo_id="Yuan20242/whisper-tiny-cpu-int8", filename="model.onnx")
session = ort.InferenceSession(model_path)
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support