Speech2Text-API / app.py
amrelshall's picture
Update app.py
281f845 verified
from transformers import pipeline
asr = pipeline(task="automatic-speech-recognition",
model="distil-whisper/distil-small.en")
import gradio as gr
demo = gr.Blocks()
# now ho to make the demo take long time audio
def transcribe_long_form(filepath):
if filepath is None:
gr.Warning("Please submit again <3 ")
return ""
output = asr(
filepath,
max_new_tokens=256,
chunk_length_s=30,
batch_size=8,
)
return output["text"]
mic_transcribe = gr.Interface(
fn=transcribe_long_form,
inputs=gr.Audio(sources="microphone",
type="filepath"),
outputs=gr.Textbox(label="Transcription",
lines=3),
allow_flagging="never")
file_transcribe = gr.Interface(
fn=transcribe_long_form,
inputs=gr.Audio(sources="upload",
type="filepath"),
outputs=gr.Textbox(label="Transcription",
lines=3),
allow_flagging="never",
)
with demo:
gr.TabbedInterface(
[mic_transcribe,
file_transcribe],
["Transcribe Microphone",
"Transcribe Audio File"])
demo.launch(share=True)