File size: 1,370 Bytes
4815e32 417ed65 4815e32 417ed65 4815e32 9482c8f 417ed65 9482c8f 417ed65 9482c8f 4815e32 417ed65 |
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 |
import gradio as gr
from transformers import pipeline
import torch
import librosa
import soundfile
SAMPLE_RATE = 16000
pipe = pipeline(model="openai/whisper-small")
def transcribe(Microphone, File_Upload):
warn_output = ""
if (Microphone is not None) and (File_Upload is not None):
warn_output = "WARNING: You've uploaded an audio file and used the microphone. " \
"The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
file = Microphone
elif (Microphone is None) and (File_Upload is None):
return "ERROR: You have to either use the microphone or upload an audio file"
elif Microphone is not None:
file = Microphone
else:
file = File_Upload
text = pipe(file)["text"]
return warn_output + text
iface = gr.Interface(
fn=transcribe,
inputs=[
gr.inputs.Audio(source="microphone", type='filepath', optional=True),
gr.inputs.Audio(source="upload", type='filepath', optional=True),
],
outputs="text",
layout="horizontal",
theme="huggingface",
title="Whisper Small",
description="Demo for multilingual speech recognition using the official OpenAI [Whisper small checkpoint](https://huggingface.co/openai/whisper-small).",
allow_flagging='never',
)
iface.launch(enable_queue=True) |