File size: 488 Bytes
fb719ed 7158f52 fb719ed |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 |
import torch
from transformers import pipeline
import numpy as np
import gradio as gr
pipe = pipeline(
"automatic-speech-recognition", model="openai/whisper-base"
)
def transcribe(audio):
sr, y = audio
# Pasamos el array de muestras a tipo NumPy de 32 bits
y = y.astype(np.float32)
y /= np.max(np.abs(y))
return pipe({"sampling_rate": sr, "raw": y})["text"]
demo = gr.Interface(
transcribe,
gr.Audio(sources=["microphone"]),
"text"
)
demo.launch() |