Create stt_app.py

stt_app.py

@@ -0,0 +1,24 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load Whisper model
+stt_pipeline = pipeline("automatic-speech-recognition", model="openai/whisper-small")
+
+def transcribe(audio):
+    if audio is None:
+        return "Please record some audio."
+    result = stt_pipeline(audio)
+    return result["text"]
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 🎙️ Speech to Text Converter")
+    gr.Markdown("Supports **English, Spanish, French, German, Portuguese, Italian, Russian, Chinese**")
+
+    with gr.Row():
+        with gr.Column():
+            audio_input = gr.Audio(sources=["microphone"], type="filepath", label="🎤 Record Speech")
+            transcribe_btn = gr.Button("Transcribe")
+        with gr.Column():
+            output_text = gr.Textbox(label="📝 Transcribed Text", lines=8)
+
+    transcribe_btn.click(fn=transcribe, inputs=audio_input, outputs=output_text)