|
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() |
|
|
|
|
|
|
|
return image_path, pre(audio) |
|
|
|
|
|
|
|
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() |
