File size: 4,166 Bytes
030ab41 73e8673 030ab41 c4e772c 030ab41 c4e772c 030ab41 c4e772c 030ab41 c4e772c 030ab41 c4e772c 030ab41 |
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 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
import gradio as gr
import requests
import json
import os
def send_req(title, audio_file_path):
url = "https://dev-phonic-api.vuihoc.vn/api/v3/get_score_from_file"
payload = {'title': title}
files=[
('audio',('temp.wav',open(audio_file_path,'rb'),'audio/wav'))
]
headers = {
'accept': 'application/json',
'Authorization': 'Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6ODg2MSwiZGV2aWNlSWQiOjg4NjEsImlhdCI6MTcxMTk2MTY2OSwiZXhwIjoxNzE3MTQ1NjY5fQ.8Wtzyx3mKVh7K9_GNzseWdK1NH-hycYdNh1uFsoVvEg'
}
response = requests.request("POST", url, headers=headers, data=payload, files=files)
return response.json()
def create_html_output(real_transcript, is_letter_correct_all_words):
html_output = "<center><h1>"
for i, char in enumerate(real_transcript):
if is_letter_correct_all_words[i] == '1':
html_output += f"<span style='color:green;'>{char}</span>"
else:
html_output += f"<span style='color:red;'>{char}</span>"
html_output += "</h1></center>"
return html_output
def create_html_output_ipa(word_score_list):
html_output = "<center><h1>"
for word_score in word_score_list:
for phone_score in word_score["phone_score_list"]:
if phone_score["quality_score"] == 100:
html_output += f"<span style='color:green;'>{phone_score['phone_ipa']}</span>"
else:
html_output += f"<span style='color:red;'>{phone_score['phone_ipa']}</span>"
html_output += "<span style='color:red;'> </span>"
html_output += "</h1></center>"
return html_output
def download_audio_file(url, filename=None):
"""
Tải xuống tệp âm thanh từ một URL và lưu nó vào đĩa.
Args:
url (str): URL của tệp âm thanh cần tải xuống.
filename (str, optional): Tên tệp để lưu (mặc định là tên tệp từ URL).
"""
response = requests.get(url)
response.raise_for_status() # Kiểm tra lỗi HTTP
# Nếu không cung cấp tên tệp, sử dụng tên tệp từ URL
if not filename:
filename = url.split("/")[-1]
with open(filename, "wb") as f:
f.write(response.content)
return filename
def pa_check(url_audio, microphone, file_upload, reference_text):
if url_audio:
file = download_audio_file(url_audio)
else:
if (microphone is not None) and (file_upload is not None):
warn_output = (
"WARNING: You've uploaded an audio file and used the microphone. "
"The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
)
elif (microphone is None) and (file_upload is None):
return "ERROR: You have to either use the microphone or upload an audio file"
file = microphone if microphone is not None else file_upload
result = send_req(reference_text, file)
try:
html_output = create_html_output(result["data"]["real_transcripts"], result["data"]["is_letter_correct_all_words"])
html_output_ipa = create_html_output_ipa(result["data"]["word_score_list"])
except Exception as e:
print(e)
print(result["data"]["real_transcripts"])
print(result["data"]["is_letter_correct_all_words"])
html_output = "ERROR: Something went wrong with the server response. Please try again later."
return json.dumps(result, indent=4, ensure_ascii=False), html_output, html_output_ipa
demo = gr.Interface(
fn=pa_check,
inputs=[
gr.Textbox(label="Url audio", type="text", placeholder="Download audio form url"),
gr.Audio(sources="microphone", type="filepath"),
gr.Audio(sources="upload", type="filepath"),
gr.Textbox(label="Reference text", type="text", placeholder="How are you?|What is your name?"),
],
outputs=[
gr.Textbox(label="Output"),
"html",
"html"
],
theme="huggingface",
title="Pronunciation Assessment",
allow_flagging="never"
)
demo.launch(auth=(os.environ['username'], os.environ['password']))
|