Spaces:
Runtime error
Runtime error
File size: 1,786 Bytes
13b9ce8 |
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 |
import torch
import gradio as gr
import pytube as pt
from transformers import pipeline
from huggingface_hub import model_info
MODEL_NAME = "openai/whisper-small" #this always needs to stay in line 8 :D sorry for the hackiness
lang = "en"
device = 0 if torch.cuda.is_available() else "cpu"
pipe = pipeline(
task="automatic-speech-recognition",
model=MODEL_NAME,
chunk_length_s=30,
device=device,
)
pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
def transcribe(microphone, file_upload):
warn_output = ""
if (microphone is not None) and (file_upload is not None):
warn_output = (
"WARNING: You've uploaded an audio file and used the microphone. "
"The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
)
elif (microphone is None) and (file_upload is None):
return "ERROR: You have to either use the microphone or upload an audio file"
file = microphone if microphone is not None else file_upload
text = pipe(file)["text"]
return warn_output + text
demo = gr.Blocks()
examples = [
['TestAudio1.mp3'], ['TestAudio2.wav'], ['TestAudio3.wav'], ['TestAudio4.wav'], ['TestAudio5.wav'], ['TestAudio6.wav'], ['TestAudio7.wav'], ['TestAudio8.wav'], ['TestAudio9.wav'], ['TestAudio10.wav']
]
mf_transcribe = gr.Interface(
fn=transcribe,
inputs=[
gr.inputs.Audio(source="microphone", type="filepath", optional=True),
gr.inputs.Audio(source="upload", type="filepath", optional=True)
],
outputs="text",
layout="horizontal",
theme="huggingface",
allow_flagging="never",
examples = examples
).launch(enable_queue=True)
#used openai/whisper model |