Create audio.py

audio.py

@@ -0,0 +1,49 @@
+import torch
+import gradio as gr
+from pathlib import Path
+from transformers import pipeline
+
+model_id = "Sandiago21/whisper-large-v2-spanish"
+
+cache_path = Path("~/.cache/huggingface/transformers") / model_id
+if not cache_path.is_dir():
+    pipe = pipeline("automatic-speech-recognition", model=model_id)
+else:
+    pipe = pipeline("automatic-speech-recognition", model=cache_path)
+
+def transcribe_speech(filepath):
+    output = pipe(
+        filepath,
+        max_new_tokens=256,
+        generate_kwargs={
+            "task": "transcribe",
+            "language": "spanish",
+        },  
+        chunk_length_s=30,
+        batch_size=8,
+    )
+    return output["text"]
+
+demo = gr.Blocks()
+
+mic_transcribe = gr.Interface(
+    fn=transcribe_speech,
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs=gr.outputs.Textbox(),
+
+)
+
+file_transcribe = gr.Interface(
+    fn=transcribe_speech,
+    inputs=gr.Audio(source="upload", type="filepath"),
+    outputs=gr.outputs.Textbox(),
+
+)
+
+with demo:
+    gr.TabbedInterface(
+        [mic_transcribe, file_transcribe],
+        ["Transcribe Microphone", "Transcribe Audio File"],
+    ),
+
+demo.launch()