import gradio as gr | |
import whisper | |
MODEL = whisper.load_model("small.en") | |
def transcribe(audio): | |
result = MODEL.transcribe(audio) | |
try: | |
return result["text"] | |
except: | |
return "" | |
examples = [["apollo11_example.mp3"], ["ariane6_example.mp3"]] | |
ui = gr.Interface( | |
fn=transcribe, | |
inputs=gr.Audio( | |
sources=["microphone", "upload"], | |
type="filepath", | |
label="Input Audio", | |
), | |
outputs=gr.Textbox( | |
label="Transcription", | |
placeholder="The transcribed text will appear here...", | |
), | |
title="ECHO", | |
description=""" | |
This is a demo of the transcription capabilities of "ECHO". This could be adapded to run real-time transcription on a live audio stream like ISS communications. | |
### How to use: | |
1. **Record or Upload**: Click on the microphone icon 🎙️ to record audio, usign your microphone, or click on the upload button ⬆️ to upload an audio file. | |
You can also use the **Examples** provided below, as inputs, by clicking on them. | |
2. **Click Submit**: Clicking the submit button will transcribe the audio. | |
3. **Read the Transcription**: The transcribed text will appear in the text box below the audio input section. | |
""", | |
examples=examples, | |
) | |
ui.launch() | |