File size: 907 Bytes
9ff8a4f |
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 29 30 31 32 33 34 35 36 |
import whisper
import gradio as gr
model = whisper.load_model("small")
def transcribe(audio):
#time.sleep(3)
# load audio and pad/trim it to fit 30 seconds
audio = whisper.load_audio(audio)
audio = whisper.pad_or_trim(audio)
# make log-Mel spectrogram and move to the same device as the model
mel = whisper.log_mel_spectrogram(audio).to(model.device)
# detect the spoken language
_, probs = model.detect_language(mel)
print(f"Detected language: {max(probs, key=probs.get)}")
# decode the audio
options = whisper.DecodingOptions(fp16 = False)
result = whisper.decode(model, mel, options)
return result.text
gr.Interface(
title = 'OpenAI Whisper ASR Gradio Web UI',
fn=transcribe,
inputs=[
gr.inputs.Audio(source="microphone", type="filepath")
],
outputs=[
"textbox"
],
live=True).launch() |