Update app.py

app.py

@@ -1,5 +1,32 @@
-git lfs install
+# Use a pipeline as a high-level helper
+from transformers import pipeline
 
-git clone https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-audio-preview
+pipe = pipeline("text-generation", model="scb10x/llama-3-typhoon-v1.5-8b-audio-preview", trust_remote_code=True)
 
-GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-audio-preview
+
+from transformers import AutoModel
+
+# Initialize from the trained model
+model = AutoModel.from_pretrained(
+    "scb10x/llama-3-typhoon-v1.5-8b-audio-preview", 
+    torch_dtype=torch.float16,
+    trust_remote_code=True
+)
+model.to("cuda")
+model.eval()
+
+# Run generation
+prompt_pattern="<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n<Speech><SpeechHere></Speech> {}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+response = model.generate(
+    wav_path="path_to_your_audio.wav",
+    prompt="transcribe this audio",
+    prompt_pattern=prompt_pattern,
+    do_sample=False,
+    max_length=1200,
+    repetition_penalty=1.1,
+    num_beams=1,
+    # temperature=0.4,
+    # top_p=0.9,
+    # streamer=streamer # supports TextIteratorStreamer
+)
+print(response)