File size: 571 Bytes
bf2b5e4 2309e11 bf2b5e4 |
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 |
import gradio as gr
from transformers import pipeline
import numpy as np
transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-tiny.en", generate_kwargs={"temperature": 1.0})
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",
)
demo.launch(share=True)
|