File size: 1,091 Bytes
a088775 08c62eb a088775 28be9e8 a088775 28be9e8 a088775 28be9e8 a088775 28be9e8 a088775 |
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 |
import whisper
import gradio as gr
import datetime
model = whisper.load_model('base')
def transcribe(inputs , timestamp):
if inputs is None:
raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
output = ""
result = model.transcribe(inputs)
if timestamp == "Yes":
for indx, segment in enumerate(result['segments']):
output += str(datetime.timedelta (seconds=segment['start'])) +" "+ str(datetime.timedelta (seconds=segment['end'])) + "\n"
output += segment['text'].strip() + '\n'
else:
output = result["text"]
return output
interface = gr.Interface(
fn=transcribe,
inputs=[gr.Audio(sources=["upload"],type="filepath"),
gr.Radio(["Yes", "No"], label="Timestamp", info="Displays with timestamp if needed."),],
outputs="text",
title="Whisper Large V3: Transcribe Audio",
description=(
"Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper API"
)
)
interface.launch() |