File size: 1,819 Bytes
3e53cd7 bc0e0ee 3e53cd7 bc0e0ee 3e53cd7 bc0e0ee 912b759 3e53cd7 bc0e0ee 3e53cd7 bc0e0ee 3e53cd7 912b759 3e53cd7 912b759 d42960c 3e53cd7 |
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 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
# 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 = 'Product Recommendation System Text',
# fn=transcribe,
# inputs=[
# gr.inputs.Audio(source="microphone", type="filepath")
# ],
# outputs=[
# "textbox"
# ],
# live=True).launch()
import whisper
import gradio as gr
model = whisper.load_model("small")
def transcribe(audio):
# Load audio and pad/trim it to fit 30 seconds
audio = whisper.load_audio(audio)
audio = whisper.pad_or_trim(audio)
# Convert to log-Mel spectrogram
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
# Update Gradio interface for the new version
gr.Interface(
title='Product Recommendation System Text',
fn=transcribe,
inputs=gr.Audio(type="filepath"), # Removed 'source' argument
outputs=gr.Textbox(),
live=True
).launch()
|