Spaces:
Sleeping
Sleeping
VenkateshRoshan
commited on
Commit
·
55d906c
1
Parent(s):
5abb6bc
App Code updated
Browse files
app.py
CHANGED
@@ -84,69 +84,159 @@
|
|
84 |
# if __name__ == '__main__' :
|
85 |
# demo.launch()
|
86 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
import requests
|
88 |
import gradio as gr
|
89 |
import tempfile
|
90 |
import os
|
91 |
from transformers import pipeline
|
92 |
from huggingface_hub import InferenceClient
|
|
|
|
|
|
|
|
|
|
|
93 |
|
94 |
model_id = "openai/whisper-large-v3"
|
95 |
client = InferenceClient(model_id)
|
96 |
-
pipe = pipeline("automatic-speech-recognition", model=model_id)
|
97 |
|
98 |
-
|
99 |
-
|
100 |
-
# raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
|
101 |
-
|
102 |
-
# text = pipe(inputs, chunk_length_s=30)["text"]
|
103 |
-
# return text
|
104 |
-
|
105 |
-
def transcribe(inputs, task):
|
106 |
if inputs is None:
|
107 |
raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
|
108 |
|
109 |
try:
|
110 |
-
|
111 |
-
|
112 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
113 |
|
114 |
except Exception as e:
|
115 |
-
return fr'Error: {str(e)}'
|
116 |
-
|
117 |
|
118 |
demo = gr.Blocks()
|
119 |
|
120 |
mf_transcribe = gr.Interface(
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
)
|
133 |
|
134 |
file_transcribe = gr.Interface(
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
)
|
147 |
|
148 |
with demo:
|
149 |
-
gr.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
150 |
|
151 |
if __name__ == "__main__":
|
152 |
-
demo.queue().launch()
|
|
|
84 |
# if __name__ == '__main__' :
|
85 |
# demo.launch()
|
86 |
|
87 |
+
# import requests
|
88 |
+
# import gradio as gr
|
89 |
+
# import tempfile
|
90 |
+
# import os
|
91 |
+
# from transformers import pipeline
|
92 |
+
# from huggingface_hub import InferenceClient
|
93 |
+
# import time
|
94 |
+
# import torch
|
95 |
+
|
96 |
+
# device = "cuda" if torch.cuda.is_available() else "cpu"
|
97 |
+
|
98 |
+
|
99 |
+
# model_id = "openai/whisper-large-v3"
|
100 |
+
# client = InferenceClient(model_id)
|
101 |
+
# pipe = pipeline("automatic-speech-recognition", model=model_id, device=device)
|
102 |
+
|
103 |
+
# # def transcribe(inputs, task):
|
104 |
+
# # if inputs is None:
|
105 |
+
# # raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
|
106 |
+
|
107 |
+
# # text = pipe(inputs, chunk_length_s=30)["text"]
|
108 |
+
# # return text
|
109 |
+
|
110 |
+
# def transcribe(inputs, task):
|
111 |
+
# start = time.time()
|
112 |
+
# if inputs is None:
|
113 |
+
# raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
|
114 |
+
|
115 |
+
# try:
|
116 |
+
|
117 |
+
# res = client.automatic_speech_recognition(inputs).text
|
118 |
+
# end = time.time() - start
|
119 |
+
# return res, end
|
120 |
+
|
121 |
+
# except Exception as e:
|
122 |
+
# return fr'Error: {str(e)}'
|
123 |
+
|
124 |
+
|
125 |
+
# demo = gr.Blocks()
|
126 |
+
|
127 |
+
# time_taken = gr.Textbox(label="Time taken", type="text")
|
128 |
+
|
129 |
+
# mf_transcribe = gr.Interface(
|
130 |
+
# fn=transcribe,
|
131 |
+
# inputs=[
|
132 |
+
# gr.Audio(sources="microphone", type="filepath"),
|
133 |
+
# gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
|
134 |
+
# ],
|
135 |
+
# outputs=["text", time_taken],
|
136 |
+
# title="Whisper Large V3: Transcribe Audio",
|
137 |
+
# description=(
|
138 |
+
# "Transcribe long-form microphone or audio inputs with the click of a button!"
|
139 |
+
# ),
|
140 |
+
# allow_flagging="never",
|
141 |
+
# )
|
142 |
+
|
143 |
+
# file_transcribe = gr.Interface(
|
144 |
+
# fn=transcribe,
|
145 |
+
# inputs=[
|
146 |
+
# gr.Audio(sources="upload", type="filepath", label="Audio file"),
|
147 |
+
# gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
|
148 |
+
# ],
|
149 |
+
# outputs=["text", time_taken],
|
150 |
+
# title="Whisper Large V3: Transcribe Audio",
|
151 |
+
# description=(
|
152 |
+
# "Transcribe long-form microphone or audio inputs with the click of a button!"
|
153 |
+
# ),
|
154 |
+
# allow_flagging="never",
|
155 |
+
# )
|
156 |
+
|
157 |
+
|
158 |
+
|
159 |
+
# with demo:
|
160 |
+
# gr.TabbedInterface([mf_transcribe, file_transcribe], ["Microphone", "Audio file"])
|
161 |
+
|
162 |
+
# if __name__ == "__main__":
|
163 |
+
# demo.queue().launch()
|
164 |
+
|
165 |
import requests
|
166 |
import gradio as gr
|
167 |
import tempfile
|
168 |
import os
|
169 |
from transformers import pipeline
|
170 |
from huggingface_hub import InferenceClient
|
171 |
+
import time
|
172 |
+
import torch
|
173 |
+
|
174 |
+
# Ensure CUDA is available and set device accordingly
|
175 |
+
# device = 0 if torch.cuda.is_available() else -1
|
176 |
|
177 |
model_id = "openai/whisper-large-v3"
|
178 |
client = InferenceClient(model_id)
|
179 |
+
pipe = pipeline("automatic-speech-recognition", model=model_id) #, device=device)
|
180 |
|
181 |
+
def transcribe(inputs, task, use_api):
|
182 |
+
start = time.time()
|
|
|
|
|
|
|
|
|
|
|
|
|
183 |
if inputs is None:
|
184 |
raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
|
185 |
|
186 |
try:
|
187 |
+
if use_api:
|
188 |
+
# Use InferenceClient (API) if checkbox is checked
|
189 |
+
res = client.automatic_speech_recognition(inputs).text
|
190 |
+
else:
|
191 |
+
# Use local pipeline if checkbox is unchecked
|
192 |
+
res = pipe(inputs, chunk_length_s=30)["text"]
|
193 |
+
|
194 |
+
end = time.time() - start
|
195 |
+
return res, end
|
196 |
|
197 |
except Exception as e:
|
198 |
+
return fr'Error: {str(e)}', None
|
|
|
199 |
|
200 |
demo = gr.Blocks()
|
201 |
|
202 |
mf_transcribe = gr.Interface(
|
203 |
+
fn=transcribe,
|
204 |
+
inputs=[
|
205 |
+
gr.Audio(sources="microphone", type="filepath"),
|
206 |
+
gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
|
207 |
+
],
|
208 |
+
outputs=["text", "text"], # Placeholder for transcribed text and time taken
|
209 |
+
title="Whisper Large V3: Transcribe Audio",
|
210 |
+
description=(
|
211 |
+
"Transcribe long-form microphone or audio inputs with the click of a button!"
|
212 |
+
),
|
213 |
+
allow_flagging="never",
|
214 |
+
)
|
215 |
|
216 |
file_transcribe = gr.Interface(
|
217 |
+
fn=transcribe,
|
218 |
+
inputs=[
|
219 |
+
gr.Audio(sources="upload", type="filepath", label="Audio file"),
|
220 |
+
gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
|
221 |
+
],
|
222 |
+
outputs=["text", "text"], # Placeholder for transcribed text and time taken
|
223 |
+
title="Whisper Large V3: Transcribe Audio",
|
224 |
+
description=(
|
225 |
+
"Transcribe long-form microphone or audio inputs with the click of a button!"
|
226 |
+
),
|
227 |
+
allow_flagging="never",
|
228 |
+
)
|
229 |
|
230 |
with demo:
|
231 |
+
with gr.Row():
|
232 |
+
# with gr.Column():
|
233 |
+
# Group the tabs for microphone and file-based transcriptions
|
234 |
+
gr.TabbedInterface([mf_transcribe, file_transcribe], ["Microphone", "Audio file"])
|
235 |
+
|
236 |
+
with gr.Column():
|
237 |
+
use_api_checkbox = gr.Checkbox(label="Use API", value=False) # Checkbox outside
|
238 |
+
time_taken = gr.Textbox(label="Time taken", type="text") # Time taken outside the interfaces
|
239 |
+
|
240 |
|
241 |
if __name__ == "__main__":
|
242 |
+
demo.queue().launch()
|