vasuans commited on
Commit
6fc0a64
Β·
verified Β·
1 Parent(s): a67898e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +60 -6
README.md CHANGED
@@ -1,14 +1,68 @@
1
  ---
2
- title: Voicepulse
3
- emoji: 🐨
4
- colorFrom: purple
5
- colorTo: red
6
  sdk: gradio
7
- sdk_version: 5.33.1
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
  short_description: Multilingual audio feedback summarizer
 
 
 
12
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
 
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
+ title: VoicePulse – Voice Feedback Summarizer
3
+ emoji: 🎧
4
+ colorFrom: yellow
5
+ colorTo: pink
6
  sdk: gradio
7
+ sdk_version: 5.32.1
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
  short_description: Multilingual audio feedback summarizer
12
+ tags:
13
+ - mcp-server-track
14
+ - agent-demo-track
15
  ---
16
+ # VoicePulse: Multilingual Voice Feedback Collector and Visualizer
17
+
18
+ VoicePulse is a multilingual voice feedback summarizer built with πŸ€— Hugging Face, Gradio, and open-source speech/translation models. Users can speak in Telugu, Hindi, Tamil, Kannada, or English. The app transcribes, translates (if needed), summarizes the feedback, and visualizes key insights using a dynamic word cloud. It also provides CSV export of all collected feedback.
19
+
20
+ ## πŸ”₯ Features
21
+
22
+ - 🎀 Voice input in 5 languages (English, Telugu, Hindi, Tamil, Kannada)
23
+ - πŸ” Auto-translation to English using Facebook NLLB
24
+ - ✨ Summarization using DistilBART
25
+ - ☁️ Word cloud generation of key terms
26
+ - πŸ“ CSV export of all feedback and summaries
27
+ - 🎧 Sample audio playback for testing in all supported languages
28
+
29
+ ## πŸš€ How to Use
30
+
31
+ 1. Speak your feedback using your microphone.
32
+ 2. Choose your spoken language from the dropdown.
33
+ 3. Click **Process Feedback**.
34
+ 4. View your summarized feedback and word cloud.
35
+ 5. Export all collected feedback to CSV if needed.
36
+ 6. Use sample buttons to try audio feedback in different languages.
37
+
38
+ ## πŸ›  Tech Stack
39
+
40
+ - **Gradio** – UI Interface
41
+ - **Hugging Face Transformers** – ASR, translation, and summarization
42
+ - **gTTS** – For generating test audio
43
+ - **pydub + matplotlib + wordcloud** – Audio trimming and visualization
44
+
45
+ ## πŸ“¦ Dependencies
46
+ Ensure you have these in your `requirements.txt`:
47
+ ```txt
48
+ gradio
49
+ transformers
50
+ nltk
51
+ wordcloud
52
+ matplotlib
53
+ pydub
54
+ torch
55
+ gtts
56
+ soundfile
57
+ ```
58
+
59
+ ## πŸ“„ Tags
60
+ `#gradio` `#huggingface` `#voice-feedback` `#multilingual` `#NLLB` `#speech-to-text` `#translation` `#summarization` `#data-viz`
61
+
62
+ ---
63
+
64
+
65
+
66
+
67
+
68