File size: 666 Bytes
90b4970 0dc0508 3c74592 d4d8b59 3c74592 90b4970 a1af285 3c74592 9bd519a 90b4970 05019fe 90b4970 a1af285 90b4970 7cefe62 660ac16 90b4970 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 |
# import gradio as gr
# gr.load("models/openai/whisper-large-v3-turbo").launch()
import gradio as gr
from transformers import pipeline
model = gr.load("models/openai/whisper-large-v3-turbo")
pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3-turbo")
# Define a function to process the output and extract only the transcription text
def process_transcription(audio_input):
result = pipe(audio_input)
# Extract the transcription text directly
transcription = result["text"]
return transcription
# Launch the interface
gr.Interface(
process_transcription,
gr.Audio(type="filepath"),
outputs="text"
).launch() |