Create app.py

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+model_id = "openai/whisper-large-v3"
+model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True)
+model.to(device)
+processor = AutoProcessor.from_pretrained(model_id)
+
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    torch_dtype=torch_dtype,
+    device=device,
+)
+
+def transcribe(audio):
+    result = pipe(audio)["text"]
+    return result
+
+iface = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs="text",
+    live=True,
+    title="Speech-to-Text Demo",
+    description="Transcribe speech to text using the Whisper model."
+)
+
+if __name__ == "__main__":
+    iface.launch()