varshamishra's picture
Update app.py
fe21998 verified
import gradio as gr
from transformers import pipeline
# Load Whisper model
model_name = "AventIQ-AI/whisper-speech-text"
stt_pipeline = pipeline("automatic-speech-recognition", model=model_name)
def transcribe(audio_path):
"""Transcribe speech to text using Whisper."""
if audio_path is None:
return "⚠️ Please upload or record an audio file."
try:
# Pass the file path directly to the Whisper pipeline
result = stt_pipeline(audio_path)
return f"📝 **Transcription:**\n{result['text']}"
except Exception as e:
return f"❌ Error processing audio: {str(e)}"
# Create Enhanced Gradio Interface
with gr.Blocks(theme="default") as demo:
gr.Markdown(
"""
# 🎤 **Whisper Speech-to-Text**
**Upload or record an audio file** and this tool will convert your speech into text using **AventIQ-AI Whisper Model**.
Supports **MP3, WAV, FLAC** formats.
"""
)
with gr.Row():
audio_input = gr.Audio(type="filepath", label="🎙️ Upload or Record Your Voice")
transcribed_text = gr.Textbox(label="📝 Transcription", interactive=False)
submit_btn = gr.Button("🎧 Transcribe", variant="primary")
submit_btn.click(transcribe, inputs=audio_input, outputs=transcribed_text)
# Launch the app
if __name__ == "__main__":
demo.launch()