Spaces:
Runtime error
Runtime error
File size: 1,768 Bytes
4644758 a5c0365 4644758 a5c0365 4644758 |
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 |
import torch
import gradio as gr
from transformers import pipeline
model_id = "Sandiago21/whisper-large-v2-german-2" # update with your model id
pipe = pipeline("automatic-speech-recognition", model=model_id)
title = "Automatic Speech Recognition (ASR)"
description = """
Demo for automatic speech recognition in German. Demo uses [Sandiago21/whisper-large-v2-german-2](https://huggingface.co/Sandiago21/whisper-large-v2-german-2) checkpoint, which is based on OpenAI's
[Whisper](https://huggingface.co/openai/whisper-large-v2) model and is fine-tuned in German Audio dataset
"""
def transcribe_speech(filepath):
output = pipe(
filepath,
max_new_tokens=256,
generate_kwargs={
"task": "transcribe",
"language": "german",
}, # update with the language you've fine-tuned on
chunk_length_s=30,
batch_size=8,
)
return output["text"]
demo = gr.Blocks()
mic_transcribe = gr.Interface(
fn=transcribe_speech,
inputs=gr.Audio(source="microphone", type="filepath"),
outputs=gr.outputs.Textbox(),
tilte=title,
description=description,
)
file_transcribe = gr.Interface(
fn=transcribe_speech,
inputs=gr.Audio(source="upload", type="filepath"),
outputs=gr.outputs.Textbox(),
examples=[["./example.wav"]],
tilte=title,
description=description,
)
with demo:
gr.TabbedInterface(
[mic_transcribe, file_transcribe],
["Transcribe Microphone", "Transcribe Audio File"],
),
demo.launch()
|