Spaces:
Running
Running
File size: 2,049 Bytes
0e97cdb |
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 68 69 70 71 72 73 74 75 76 |
import gradio as gr
from transformers import pipeline
pipe2 = pipeline("automatic-speech-recognition", model="distil-whisper/distil-small.en")
pipe3 = pipeline("automatic-speech-recognition", model="antony66/whisper-large-v3-russian")
demo = gr.Blocks()
def transcribe_speech_english(filepath):
if filepath is None:
gr.Warning("No audio found, please retry.")
return ""
output = pipe2(filepath)
return output["text"]
def transcribe_speech_russian(filepath):
if filepath is None:
gr.Warning("No audio found, please retry.")
return ""
output = pipe3(filepath)
return output["text"]
mic_transcribe_english = gr.Interface(
fn=transcribe_speech_english,
inputs=gr.Audio(sources="microphone",
type="filepath"),
outputs=gr.Textbox(label="Transcription",
lines=3),
allow_flagging="never")
mic_transcribe_russian = gr.Interface(
fn=transcribe_speech_russian,
inputs=gr.Audio(sources="microphone",
type="filepath"),
outputs=gr.Textbox(label="Transcription",
lines=3),
allow_flagging="never")
file_transcribe_english = gr.Interface(
fn=transcribe_speech_english,
inputs=gr.Audio(sources="upload",
type="filepath"),
outputs=gr.Textbox(label="Transcription",
lines=3),
allow_flagging="never",
)
file_transcribe_russian = gr.Interface(
fn=transcribe_speech_russian,
inputs=gr.Audio(sources="upload",
type="filepath"),
outputs=gr.Textbox(label="Transcription",
lines=3),
allow_flagging="never",
)
with demo:
gr.TabbedInterface(
[mic_transcribe_english,
file_transcribe_english,
mic_transcribe_russian,
file_transcribe_russian],
["Transcribe Microphone English",
"Transcribe Audio File English",
"Transcribe Microphone Russian",
"Transcribe Audio File Russian"],
)
demo.launch() |