mistralai
/

Voxtral-Mini-3B-2507

@@ -512,7 +512,7 @@ repo_id = "mistralai/Voxtral-Mini-3B-2507"
 processor = AutoProcessor.from_pretrained(repo_id)
 model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
-inputs = processor.apply_transcrition_request(language="en", audio="https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3", model_id=repo_id)
 inputs = inputs.to(device, dtype=torch.bfloat16)
 outputs = model.generate(**inputs, max_new_tokens=500)

 processor = AutoProcessor.from_pretrained(repo_id)
 model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
+inputs = processor.apply_transcription_request(language="en", audio="https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3", model_id=repo_id)
 inputs = inputs.to(device, dtype=torch.bfloat16)
 outputs = model.generate(**inputs, max_new_tokens=500)