Spaces:
Sleeping
Sleeping
File size: 1,323 Bytes
e3ca44c f77c608 952954d |
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 |
# pip install transformers
from transformers import pipeline
import gradio as gr
model = pipeline(model="openai/whisper-base")
en_jp_translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-jap")
# "automatic-speech-recognition"
# transcriber = pipeline(model="openai/whisper-base")
# transcriber("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/1.flac")
def transcribe_audio(mic=None, file=None):
if mic is not None:
audio = mic
elif file is not None:
audio = file
else:
return "You must either provide a mic recording or a file"
transcription = model(audio)["text"]
return transcription
def translate_text(transcription):
return en_jp_translator(transcription)[0]["translation_text"]
def combined_function(b):
transcribe_audio(inputs=audio_file, outputs=text)
translate_text(inputs=text, outputs=translate)
demo = gr.Blocks()
with demo:
audio_file = gr.Audio(type="filepath")
text = gr.Textbox()
translate = gr.Textbox()
# b1 = gr.Button("Recognize Speech & Translate")
b1 = gr.Button("Recognize Speech")
b2 = gr.Button("Translate")
# b1.click(combined_function)
b1.click(transcribe_audio, inputs=audio_file, outputs=text)
b2.click(translate_text, inputs=text, outputs= translate)
demo.launch() |