Spaces:
Sleeping
Sleeping
File size: 596 Bytes
a469909 c2b5789 f2be7cd c2b5789 a469909 3f5ff90 06ed778 3f5ff90 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 |
import gradio as gr
from transformers import pipeline, AutoModelForCTC, AutoTokenizer
# Load the model from PyTorch weights
model_name = "facebook/wav2vec2-large-xlsr-53-spanish"
model = AutoModelForCTC.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Create the ASR pipeline
trans = pipeline("automatic-speech-recognition", model=model, tokenizer=tokenizer)
def audio2text(audio):
text = trans(audio)["text"]
return text
gr.Interface(
fn=audio2text,
inputs = [gr.Audio(source="microphone", type="filepath")],
outputs=["textbox"]
).launch() |