Create app.py

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+import logging
+from transformers import pipeline
+import torch
+
+description = "Simple Speech Recognition App"
+title = "This app allows users to record audio through the microphone or upload audio files to be transcribed into text. It uses the speech_recognition library to process audio and extract spoken words. Ideal for quick transcription of short speeches and audio notes."
+
+asr = pipeline(task="automatic-speech-recognition",
+               model="distil-whisper/distil-small.en")
+
+# Adjusted function assuming 'asr' expects a file path as input
+def transcribe_speech(audio_file_path):
+    if not audio_file_path:
+        logging.error("No audio file provided.")
+        return "No audio found, please retry."
+    try:
+        logging.info(f"Processing file: {audio_file_path}")
+        output = asr(audio_file_path)  # Assuming `asr` directly takes a file path
+        return output["text"]
+    except Exception as e:
+        logging.error(f"Error during transcription: {str(e)}")
+        return f"Error processing the audio file: {str(e)}"
+
+logging.basicConfig(level=logging.INFO)
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        gr.Markdown("# Simple Speech Recognition App")
+    with gr.Row():
+        gr.Markdown("### This app allows you to record or upload audio and see its transcription. Powered by the speech_recognition library.")
+    with gr.Row():
+        mic = gr.Audio(label="Record from Microphone or Upload File", type="filepath")
+        transcribe_button = gr.Button("Transcribe Audio")
+    with gr.Row():
+        transcription = gr.Textbox(label="Transcription", lines=3, placeholder="Transcription will appear here...")
+
+    transcribe_button.click(transcribe_speech, inputs=mic, outputs=transcription)
+
+demo.launch(share=True)