Spaces:
Runtime error
Runtime error
File size: 1,571 Bytes
64db4c7 9c94255 64db4c7 28bbb3d 64db4c7 28bbb3d b63a826 28bbb3d b63a826 9c94255 b63a826 64db4c7 b63a826 ff97a84 64db4c7 28bbb3d b63a826 28bbb3d b63a826 9c94255 b63a826 64db4c7 28bbb3d |
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 |
import gradio as gr
import torch
from transformers import pipeline
import numpy as np
import time
pipe_base = pipeline("automatic-speech-recognition", model="aitor-medrano/lara-base-pushed")
pipe_small = pipeline("automatic-speech-recognition", model="aitor-medrano/whisper-small-lara")
pipe_base_1600 = pipeline("automatic-speech-recognition", model="aitor-medrano/whisper-base-lara-1600")
def greet(grabacion):
inicio = time.time()
sr, y = grabacion
# Pasamos el array de muestras a tipo NumPy de 32 bits
y = y.astype(np.float32)
y /= np.max(np.abs(y))
result_base = "base:" + pipe_base({"sampling_rate": sr, "raw": y})["text"]
fin_base = time.time()
result_small = "small:" + pipe_small({"sampling_rate": sr, "raw": y})["text"]
fin_small = time.time()
result_base_1600 = "base_2000:" + pipe_base_1600({"sampling_rate": sr, "raw": y})["text"]
fin_1600 = time.time()
fin = time.time()
return result_base, fin_base - inicio, result_small, fin_small - inicio, result_base_1600, fin_1600 - inicio, fin - inicio
#return result_base, result_small, fin - inicio
demo = gr.Interface(fn=greet,
inputs=[
gr.Audio(),
],
outputs=[
gr.Text(label="Salida (Base)"),
gr.Number(label="Tiempo (Base)")
gr.Text(label="Salida (Small)"),
gr.Number(label="Tiempo (Small)")
gr.Text(label="Salida (Base 1600)"),
gr.Number(label="Tiempo (1600)")
gr.Number(label="Tiempo")
])
demo.launch()
|