Spaces:
Sleeping
Sleeping
VenkateshRoshan
commited on
Commit
·
00e87f4
1
Parent(s):
55d906c
App Code updated
Browse files
app.py
CHANGED
@@ -84,84 +84,6 @@
|
|
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
|
@@ -185,9 +107,11 @@ def transcribe(inputs, task, use_api):
|
|
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 |
|
@@ -197,15 +121,19 @@ def transcribe(inputs, task, use_api):
|
|
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!"
|
@@ -217,9 +145,10 @@ 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!"
|
@@ -231,12 +160,11 @@ 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()
|
|
|
84 |
# if __name__ == '__main__' :
|
85 |
# demo.launch()
|
86 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
import requests
|
88 |
import gradio as gr
|
89 |
import tempfile
|
|
|
107 |
|
108 |
try:
|
109 |
if use_api:
|
110 |
+
print(f'Using API for transcription...')
|
111 |
# Use InferenceClient (API) if checkbox is checked
|
112 |
res = client.automatic_speech_recognition(inputs).text
|
113 |
else:
|
114 |
+
print(f'Using local pipeline for transcription...')
|
115 |
# Use local pipeline if checkbox is unchecked
|
116 |
res = pipe(inputs, chunk_length_s=30)["text"]
|
117 |
|
|
|
121 |
except Exception as e:
|
122 |
return fr'Error: {str(e)}', None
|
123 |
|
124 |
+
def calculate_time_taken(start_time):
|
125 |
+
return time.time() - start_time
|
126 |
+
|
127 |
demo = gr.Blocks()
|
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 |
+
gr.Checkbox(label="Use API", value=False)
|
135 |
],
|
136 |
+
outputs=["text",gr.Textbox(label="Time taken", type="text")], # Placeholder for transcribed text and time taken
|
137 |
title="Whisper Large V3: Transcribe Audio",
|
138 |
description=(
|
139 |
"Transcribe long-form microphone or audio inputs with the click of a button!"
|
|
|
145 |
fn=transcribe,
|
146 |
inputs=[
|
147 |
gr.Audio(sources="upload", type="filepath", label="Audio file"),
|
148 |
+
# gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
|
149 |
+
gr.Checkbox(label="Use API", value=False) # Checkbox for API usage
|
150 |
],
|
151 |
+
outputs=["text",gr.Textbox(label="Time taken", type="text")], # Placeholder for transcribed text and time taken
|
152 |
title="Whisper Large V3: Transcribe Audio",
|
153 |
description=(
|
154 |
"Transcribe long-form microphone or audio inputs with the click of a button!"
|
|
|
160 |
with gr.Row():
|
161 |
# with gr.Column():
|
162 |
# Group the tabs for microphone and file-based transcriptions
|
163 |
+
tab = gr.TabbedInterface([mf_transcribe, file_transcribe], ["Microphone", "Audio file"])
|
|
|
|
|
|
|
|
|
164 |
|
165 |
+
# with gr.Column():
|
166 |
+
# use_api_checkbox = gr.Checkbox(label="Use API", value=False) # Checkbox outside
|
167 |
+
# # time_taken = gr.Textbox(label="Time taken", type="text") # Time taken outside the interfaces
|
168 |
|
169 |
if __name__ == "__main__":
|
170 |
+
demo.queue().launch()
|