File size: 940 Bytes
0e20c4d
 
d1dd3f0
0e20c4d
d1dd3f0
 
 
 
 
 
 
 
 
 
 
0e20c4d
d1dd3f0
 
 
0e20c4d
d1dd3f0
 
 
 
 
0e20c4d
d1dd3f0
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
import torch
from transformers import pipeline
import gradio as gr

# Function to transcribe audio using the OpenAI Whisper model
def transcript_audio(audio_file):
    # Initialize the speech recognition pipeline
    pipe = pipeline(
        "automatic-speech-recognition",
        model="openai/whisper-tiny.en",
        chunk_length_s=30,
    )
    # Transcribe the audio file and return the result
    result = pipe(audio_file, batch_size=8)["text"]
    return result

# Set up Gradio interface
audio_input = gr.Audio(sources="upload", type="filepath")  # Audio input
output_text = gr.Textbox()  # Text output

# Create the Gradio interface with the function, inputs, and outputs
iface = gr.Interface(fn=transcript_audio, 
                     inputs=audio_input, outputs=output_text, 
                     title="Audio Transcription App",
                     description="Upload the audio file")

# Launch the Gradio app
iface.launch()