import os
import gradio as gr
import time
import requests
list_stack=[]
api_url="https://90f6-34-16-143-189.ngrok-free.app/upload"
def get_transcription_whissper_api(audio,api_url=api_url):
audio_file = open(audio, 'rb')
files = {'audio': ('audio.wav', audio_file)}
response = requests.post(api_url, files=files)
json_response = response.json()
if response.status_code == 200:
print("Audio file uploaded successfully.")
return(json_response['message'])
else:
return("Error uploading the audio file.")
def empty_list():
list_stack.clear()
def inference_upload(audio,state=""):
state+= get_transcription_whissper_api(audio)+" "
return (state,state)
def inference(audio,state=""):
state += get_transcription_whissper_api(audio) + " "
delimiter=" "
list_stack.append(state)
all_transcriptions=(delimiter.join(list_stack))
return (state,all_transcriptions)
css = """
.gradio-container {
font-family: 'IBM Plex Sans', sans-serif;
}
.gr-button {
color: white;
border-color: black;
background: black;
}
input[type='range'] {
accent-color: black;
}
.dark input[type='range'] {
accent-color: #dfdfdf;
}
.container {
max-width: 1030px;
margin: auto;
padding-top: 1.5rem;
}
.details:hover {
text-decoration: underline;
}
.gr-button {
white-space: nowrap;
}
.gr-button:focus {
border-color: rgb(147 197 253 / var(--tw-border-opacity));
outline: none;
box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
--tw-border-opacity: 1;
--tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
--tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
--tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
--tw-ring-opacity: .5;
}
.footer {
margin-bottom: 45px;
margin-top: 35px;
text-align: center;
border-bottom: 1px solid #e5e5e5;
}
.footer>p {
font-size: .8rem;
display: inline-block;
padding: 0 10px;
transform: translateY(10px);
background: white;
}
.dark .footer {
border-color: #303030;
}
.dark .footer>p {
background: #0b0f19;
}
.prompt h4{
margin: 1.25em 0 .25em 0;
font-weight: bold;
font-size: 115%;
}
.animate-spin {
animation: spin 1s linear infinite;
}
@keyframes spin {
from {
transform: rotate(0deg);
}
to {
transform: rotate(360deg);
}
}
#share-btn-container {
display: flex; margin-top: 1.5rem !important; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
}
#share-btn {
all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;
}
#share-btn * {
all: unset;
}
"""
block = gr.Blocks(css=css)
with block:
gr.HTML(
"""
<div style="text-align: center; max-width: 1050px; margin: 0 auto;">
<div
style="
display: inline-flex;
align-items: center;
gap: 0.8rem;
font-size: 1.75rem;
"
>
<svg
width="0.65em"
height="0.65em"
viewBox="0 0 115 115"
fill="none"
xmlns="http://www.w3.org/2000/svg"
>
<rect width="23" height="23" fill="white"></rect>
<rect y="69" width="23" height="23" fill="white"></rect>
<rect x="23" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="23" y="69" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="46" width="23" height="23" fill="white"></rect>
<rect x="46" y="69" width="23" height="23" fill="white"></rect>
<rect x="69" width="23" height="23" fill="black"></rect>
<rect x="69" y="69" width="23" height="23" fill="black"></rect>
<rect x="92" width="23" height="23" fill="#D9D9D9"></rect>
<rect x="92" y="69" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="115" y="46" width="23" height="23" fill="white"></rect>
<rect x="115" y="115" width="23" height="23" fill="white"></rect>
<rect x="115" y="69" width="23" height="23" fill="#D9D9D9"></rect>
<rect x="92" y="46" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="92" y="115" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="92" y="69" width="23" height="23" fill="white"></rect>
<rect x="69" y="46" width="23" height="23" fill="white"></rect>
<rect x="69" y="115" width="23" height="23" fill="white"></rect>
<rect x="69" y="69" width="23" height="23" fill="#D9D9D9"></rect>
<rect x="46" y="46" width="23" height="23" fill="black"></rect>
<rect x="46" y="115" width="23" height="23" fill="black"></rect>
<rect x="46" y="69" width="23" height="23" fill="black"></rect>
<rect x="23" y="46" width="23" height="23" fill="#D9D9D9"></rect>
<rect x="23" y="115" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="23" y="69" width="23" height="23" fill="black"></rect>
</svg>
<h1 style="font-weight: 900; margin-bottom: 7px;">
Experiment Whisper via API
</h1>
</div>
<p style="margin-bottom: 10px; font-size: 94%">
This page can be used to simply try out the capabilities of tagaloc + english transcription. The model used is the smallest because this process only runs with small computations. Speed and accuracy can be improved with more powerful computing.</p>
</div>
"""
)
with gr.Group():
with gr.Box():
with gr.Row().style(mobile_collapse=False, equal_height=True):
audio = gr.Audio(
label="Input voice",
source="microphone",
type="filepath",
# streaming=True
every=4
)
audio_file_upload = gr.Audio(
label="Input From Example",
source="upload",
type="filepath",
)
btn_clear = gr.Button("Clear")
btn_trnscribe = gr.Button("Transcribe")
text = gr.Textbox(label="Transcriptions Now", elem_id="result-textarea")
text_all = gr.Textbox(label="All Transcriptions", elem_id="result-textarea")
btn_clear.click(empty_list)
btn_trnscribe.click(inference_upload,inputs=audio_file_upload,outputs=[text,text_all],show_progress="minimal")
audio.stream(inference,inputs=audio,outputs=[text,text_all],show_progress="minimal")
gr.HTML("""
<h2 style="font-weight: 900; margin: 7px;">
Tagaloc audio
</h2>
""")
example_gr_bark = gr.Examples(
examples=[
["#1 How mature are you as a Christian Ptr Joey.mp3"],
["#2 Masakit Pero May Dahilan.mp3"]
],
inputs = audio_file_upload
)
gr.HTML('''
<div class="footer">
<p>Model by openAI</a> - Gradio Demo by 🤗 Hugging Face
</p>
</div>
''')
if __name__ == "__main__":
block.launch(debug=True)