again

app.py

@@ -30,23 +30,15 @@ def run_phi4(audio_path: str, instruction: str) -> str:
     if not audio_path:
         return "Please upload an audio file."
 
-    messages = [
-        {
-            "role": "user",
-            "content": [
-                {"type": "audio", "url": audio_path},
-                {"type": "text", "text": "Transcribe the audio to text, and then translate the audio to French. Use <sep> as a separator between the origina transcript and the translation."},
-            ],
-        },
-    ]
-
-    inputs = processor.apply_chat_template(
-        messages,
-        add_generation_prompt=True,
-        tokenize=True,
-        return_dict=True,
-        return_tensors="pt",
-    ).to(model.device)
+    audio, samplerate = sf.read(audio_path)
+
+    user_prompt = "<|user|>"
+    assistant_prompt = "<|assistant|>"
+    prompt_suffix = "<|end|>"
+
+    prompt = f"{user_prompt}<|audio_1|>{instruction}{prompt_suffix}{assistant_prompt}"
+
+    inputs = processor(text=prompt, audios=[(audio, samplerate)], return_tensors="pt").to(model.device)
 
     output_ids = model.generate(
         **inputs,