Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -1,18 +1,3 @@
|
|
1 |
-
import torch
|
2 |
-
|
3 |
-
import gradio as gr
|
4 |
-
|
5 |
-
from transformers import T5ForConditionalGeneration, T5Tokenizer
|
6 |
-
|
7 |
-
import os
|
8 |
-
|
9 |
-
#import whisper
|
10 |
-
|
11 |
-
import matplotlib as plt
|
12 |
-
|
13 |
-
# whisper_model = whisper.load_model('large-v2') # Whisper 모델을 불러오기
|
14 |
-
|
15 |
-
|
16 |
path = "Hyeonsieun/NTtoGT_1epoch"
|
17 |
tokenizer = T5Tokenizer.from_pretrained(path)
|
18 |
model = T5ForConditionalGeneration.from_pretrained(path)
|
@@ -42,144 +27,5 @@ def do_correction(text):
|
|
42 |
)
|
43 |
return corrected_sentence
|
44 |
|
45 |
-
# corrected_sentence = do_correction(sentence, model, tokenizer)
|
46 |
-
|
47 |
|
48 |
gr.Interface(fn=do_correction, inputs="text", outputs="text").launch()
|
49 |
-
|
50 |
-
|
51 |
-
'''
|
52 |
-
pipe = pipeline(
|
53 |
-
task="automatic-speech-recognition",
|
54 |
-
model=MODEL_NAME,
|
55 |
-
chunk_length_s=30,
|
56 |
-
device=device,
|
57 |
-
)
|
58 |
-
|
59 |
-
|
60 |
-
def transcribe(inputs, task):
|
61 |
-
if inputs is None:
|
62 |
-
raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
|
63 |
-
|
64 |
-
text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
|
65 |
-
return text
|
66 |
-
|
67 |
-
|
68 |
-
def _return_yt_html_embed(yt_url):
|
69 |
-
video_id = yt_url.split("?v=")[-1]
|
70 |
-
HTML_str = (
|
71 |
-
f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
|
72 |
-
" </center>"
|
73 |
-
)
|
74 |
-
return HTML_str
|
75 |
-
|
76 |
-
def download_yt_audio(yt_url, filename):
|
77 |
-
info_loader = youtube_dl.YoutubeDL()
|
78 |
-
|
79 |
-
try:
|
80 |
-
info = info_loader.extract_info(yt_url, download=False)
|
81 |
-
except youtube_dl.utils.DownloadError as err:
|
82 |
-
raise gr.Error(str(err))
|
83 |
-
|
84 |
-
file_length = info["duration_string"]
|
85 |
-
file_h_m_s = file_length.split(":")
|
86 |
-
file_h_m_s = [int(sub_length) for sub_length in file_h_m_s]
|
87 |
-
|
88 |
-
if len(file_h_m_s) == 1:
|
89 |
-
file_h_m_s.insert(0, 0)
|
90 |
-
if len(file_h_m_s) == 2:
|
91 |
-
file_h_m_s.insert(0, 0)
|
92 |
-
file_length_s = file_h_m_s[0] * 3600 + file_h_m_s[1] * 60 + file_h_m_s[2]
|
93 |
-
|
94 |
-
if file_length_s > YT_LENGTH_LIMIT_S:
|
95 |
-
yt_length_limit_hms = time.strftime("%HH:%MM:%SS", time.gmtime(YT_LENGTH_LIMIT_S))
|
96 |
-
file_length_hms = time.strftime("%HH:%MM:%SS", time.gmtime(file_length_s))
|
97 |
-
raise gr.Error(f"Maximum YouTube length is {yt_length_limit_hms}, got {file_length_hms} YouTube video.")
|
98 |
-
|
99 |
-
ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"}
|
100 |
-
|
101 |
-
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
|
102 |
-
try:
|
103 |
-
ydl.download([yt_url])
|
104 |
-
except youtube_dl.utils.ExtractorError as err:
|
105 |
-
raise gr.Error(str(err))
|
106 |
-
|
107 |
-
|
108 |
-
def yt_transcribe(yt_url, task, max_filesize=75.0):
|
109 |
-
html_embed_str = _return_yt_html_embed(yt_url)
|
110 |
-
|
111 |
-
with tempfile.TemporaryDirectory() as tmpdirname:
|
112 |
-
filepath = os.path.join(tmpdirname, "video.mp4")
|
113 |
-
download_yt_audio(yt_url, filepath)
|
114 |
-
with open(filepath, "rb") as f:
|
115 |
-
inputs = f.read()
|
116 |
-
|
117 |
-
inputs = ffmpeg_read(inputs, pipe.feature_extractor.sampling_rate)
|
118 |
-
inputs = {"array": inputs, "sampling_rate": pipe.feature_extractor.sampling_rate}
|
119 |
-
|
120 |
-
text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
|
121 |
-
|
122 |
-
return html_embed_str, text
|
123 |
-
|
124 |
-
|
125 |
-
demo = gr.Blocks()
|
126 |
-
|
127 |
-
mf_transcribe = gr.Interface(
|
128 |
-
fn=transcribe,
|
129 |
-
inputs=[
|
130 |
-
gr.inputs.Audio(source="microphone", type="filepath", optional=True),
|
131 |
-
gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
|
132 |
-
],
|
133 |
-
outputs="text",
|
134 |
-
layout="horizontal",
|
135 |
-
theme="huggingface",
|
136 |
-
title="Whisper Large V3: Transcribe Audio",
|
137 |
-
description=(
|
138 |
-
"Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper"
|
139 |
-
f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
|
140 |
-
" of arbitrary length."
|
141 |
-
),
|
142 |
-
allow_flagging="never",
|
143 |
-
)
|
144 |
-
|
145 |
-
file_transcribe = gr.Interface(
|
146 |
-
fn=transcribe,
|
147 |
-
inputs=[
|
148 |
-
gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Audio file"),
|
149 |
-
gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
|
150 |
-
],
|
151 |
-
outputs="text",
|
152 |
-
layout="horizontal",
|
153 |
-
theme="huggingface",
|
154 |
-
title="Whisper Large V3: Transcribe Audio",
|
155 |
-
description=(
|
156 |
-
"Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper"
|
157 |
-
f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
|
158 |
-
" of arbitrary length."
|
159 |
-
),
|
160 |
-
allow_flagging="never",
|
161 |
-
)
|
162 |
-
|
163 |
-
yt_transcribe = gr.Interface(
|
164 |
-
fn=yt_transcribe,
|
165 |
-
inputs=[
|
166 |
-
gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
|
167 |
-
gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe")
|
168 |
-
],
|
169 |
-
outputs=["html", "text"],
|
170 |
-
layout="horizontal",
|
171 |
-
theme="huggingface",
|
172 |
-
title="Whisper Large V3: Transcribe YouTube",
|
173 |
-
description=(
|
174 |
-
"Transcribe long-form YouTube videos with the click of a button! Demo uses the OpenAI Whisper checkpoint"
|
175 |
-
f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of"
|
176 |
-
" arbitrary length."
|
177 |
-
),
|
178 |
-
allow_flagging="never",
|
179 |
-
)
|
180 |
-
|
181 |
-
with demo:
|
182 |
-
gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
|
183 |
-
|
184 |
-
demo.launch(enable_queue=True)
|
185 |
-
'''
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
path = "Hyeonsieun/NTtoGT_1epoch"
|
2 |
tokenizer = T5Tokenizer.from_pretrained(path)
|
3 |
model = T5ForConditionalGeneration.from_pretrained(path)
|
|
|
27 |
)
|
28 |
return corrected_sentence
|
29 |
|
|
|
|
|
30 |
|
31 |
gr.Interface(fn=do_correction, inputs="text", outputs="text").launch()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|