Spaces:
Runtime error
Runtime error
Commit
·
b037802
1
Parent(s):
ac89e80
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
|
| 3 |
+
def main():
|
| 4 |
+
title = """<h1 align="center">🎤 Multilingual ASR 💬</h1>"""
|
| 5 |
+
description = """
|
| 6 |
+
💻 This demo showcases a general-purpose speech recognition model called Whisper. It is trained on a large dataset of diverse audio and supports multilingual speech recognition, speech translation, and language identification tasks.<br><br>
|
| 7 |
+
<br>
|
| 8 |
+
⚙️ Components of the tool:<br>
|
| 9 |
+
<br>
|
| 10 |
+
- Real-time multilingual speech recognition<br>
|
| 11 |
+
- Language identification<br>
|
| 12 |
+
- Sentiment analysis of the transcriptions<br>
|
| 13 |
+
<br>
|
| 14 |
+
🎯 The sentiment analysis results are provided as a dictionary with different emotions and their corresponding scores.<br>
|
| 15 |
+
<br>
|
| 16 |
+
😃 The sentiment analysis results are displayed with emojis representing the corresponding sentiment.<br>
|
| 17 |
+
<br>
|
| 18 |
+
✅ The higher the score for a specific emotion, the stronger the presence of that emotion in the transcribed text.<br>
|
| 19 |
+
<br>
|
| 20 |
+
❓ Use the microphone for real-time speech recognition.<br>
|
| 21 |
+
<br>
|
| 22 |
+
⚡️ The model will transcribe the audio and perform sentiment analysis on the transcribed text.<br>
|
| 23 |
+
"""
|
| 24 |
+
|
| 25 |
+
custom_css = """
|
| 26 |
+
#banner-image {
|
| 27 |
+
display: block;
|
| 28 |
+
margin-left: auto;
|
| 29 |
+
margin-right: auto;
|
| 30 |
+
}
|
| 31 |
+
#chat-message {
|
| 32 |
+
font-size: 14px;
|
| 33 |
+
min-height: 300px;
|
| 34 |
+
}
|
| 35 |
+
"""
|
| 36 |
+
|
| 37 |
+
block = gr.Blocks(css=custom_css)
|
| 38 |
+
|
| 39 |
+
with block:
|
| 40 |
+
gr.HTML(title)
|
| 41 |
+
|
| 42 |
+
with gr.Row():
|
| 43 |
+
with gr.Column():
|
| 44 |
+
gr.HTML(description)
|
| 45 |
+
|
| 46 |
+
with gr.Group():
|
| 47 |
+
with gr.Box():
|
| 48 |
+
audio = gr.Audio(
|
| 49 |
+
label="Input Audio",
|
| 50 |
+
show_label=False,
|
| 51 |
+
source="microphone",
|
| 52 |
+
type="filepath"
|
| 53 |
+
)
|
| 54 |
+
|
| 55 |
+
sentiment_option = gr.Radio(
|
| 56 |
+
choices=["Sentiment Only", "Sentiment + Score"],
|
| 57 |
+
label="Select an option",
|
| 58 |
+
default="Sentiment Only"
|
| 59 |
+
)
|
| 60 |
+
|
| 61 |
+
btn = gr.Button("Transcribe")
|
| 62 |
+
|
| 63 |
+
lang_str = gr.Textbox(label="Language")
|
| 64 |
+
|
| 65 |
+
text = gr.Textbox(label="Transcription")
|
| 66 |
+
|
| 67 |
+
sentiment_output = gr.Textbox(label="Sentiment Analysis Results", output=True)
|
| 68 |
+
|
| 69 |
+
prediction = gr.Textbox(label="Prediction")
|
| 70 |
+
|
| 71 |
+
language_translation = gr.Textbox(label="Language Translation")
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
btn.click(inference, inputs=[audio, sentiment_option], outputs=[lang_str, text, sentiment_output, prediction,language_translation])
|
| 75 |
+
|
| 76 |
+
# gr.HTML('''
|
| 77 |
+
# <div class="footer">
|
| 78 |
+
# <p>Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a>
|
| 79 |
+
# </p>
|
| 80 |
+
# </div>
|
| 81 |
+
# ''')
|
| 82 |
+
|
| 83 |
+
block.launch()
|