File size: 793 Bytes
8e73cee f9a373a 8e73cee f9a373a 8e73cee f9a373a 8e73cee |
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 |
import gradio as gr
from transformers import pipeline
import numpy as np
import os
from huggingface_hub import login
import spaces
# Get token from Space secrets
HF_TOKEN = os.environ.get("HF_TOKEN")
if HF_TOKEN:
login(token=HF_TOKEN)
# Load model from your private repo
MODEL_ID = "badrex/JASR" # Change this to match your repo!
transcriber = pipeline("automatic-speech-recognition", model=MODEL_ID)
@spaces.GPU
def transcribe(audio):
sr, y = audio
# Convert to mono if stereo
if y.ndim > 1:
y = y.mean(axis=1)
y = y.astype(np.float32)
y /= np.max(np.abs(y))
return transcriber({"sampling_rate": sr, "raw": y})["text"]
demo = gr.Interface(
transcribe,
gr.Audio(sources="microphone"),
"text",
)
if __name__ == "__main__":
demo.launch() |