File size: 1,278 Bytes
f213555 ac01485 f213555 |
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 |
import gradio as gr
import librosa
import matplotlib.pyplot as plt
from train import ASR_Model
from model_cnn import Model
def pre(audio):
model = ASR_Model(device='cpu',model_path='model.pth',pinyin_path ='pinyin.txt')
result = model.predict(audio)
s = ''
for r in result:
s += r[0]+str(r[1])+' '
return s
def visualize(audio):
y, sr = librosa.load(audio, sr=None)
plt.figure(figsize=(10, 4))
librosa.display.waveshow(y, sr=sr)
plt.title("Waveform of the Audio")
plt.xlabel("Time (s)")
plt.ylabel("Amplitude")
image_path = "./waveform.png"
plt.savefig(image_path, format='png')
plt.close()
# print(audio)
return image_path, pre(audio)
#e = gr.Examples(examples=['./SSB10500228.wav'], inputs=[gr.File(type="filepath")])
demo = gr.Interface(fn=visualize, inputs=gr.File(file_types=['.wav'], label="wav file"),
outputs=[gr.Image(type="filepath", label="Waveform"),
gr.Textbox(type="text", label="Tone Evaluation Result")],
examples=["Examples/中原石化加油站.wav", "Examples/你叫什么名字你的名字.wav", "Examples/来一首许多年以后.wav"],
title="Mandarin Tone Evaluation")
demo.launch() |