ajnx014 commited on
Commit
3daa38c
Β·
verified Β·
1 Parent(s): 5608b3d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -1
README.md CHANGED
@@ -8,4 +8,88 @@ sdk_version: 5.17.1
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
+ ---
12
+
13
+ # πŸŽ™οΈ Voice Recognition with Similarity Testing
14
+
15
+ Welcome to the **Voice Recognition with Similarity Testing** project, built using **Gradio**, **Librosa**, and **Resemblyzer**. This application compares uploaded voice samples against reference embeddings to determine similarity, making it ideal for voice authentication and verification tasks.
16
+
17
+ ---
18
+
19
+ ## πŸš€ **Key Features**
20
+ - **Real-time Voice Verification:** Instantly compares a test voice against reference samples.
21
+ - **Multi-File Training:** Upload up to **50** audio samples for robust training.
22
+ - **Similarity Scoring:** Generates a similarity score, with results interpreted as a match or mismatch.
23
+ - **User-Friendly Interface:** Powered by **Gradio**, ensuring a seamless and interactive experience.
24
+
25
+ ---
26
+
27
+ ## πŸ› οΈ **Technology Stack**
28
+ - **Framework:** Gradio
29
+ - **Audio Processing:** Librosa
30
+ - **Voice Embeddings:** Resemblyzer
31
+ - **Numerical Computations:** NumPy
32
+ - **Audio File Handling:** SoundFile
33
+
34
+ ---
35
+
36
+ ## πŸ“ **File Structure**
37
+ ```plaintext
38
+ voice-recognition-app
39
+ β”‚
40
+ β”œβ”€β”€ app.ipynb # Main application notebook
41
+ β”œβ”€β”€ requirements.txt # Required packages
42
+ └── README.md # Project documentation
43
+ ```
44
+
45
+ ---
46
+
47
+ ## πŸ’Ύ **Usage**
48
+ 1. **Train the Model:** Upload up to **50** `.wav` files as reference samples.
49
+ 2. **Test a Voice:** Upload a single `.wav` file and receive a similarity score.
50
+ 3. **Interpret Results:** Scores above **0.80** indicate a close match.
51
+
52
+ ---
53
+
54
+ ## πŸ“¦ **Dependencies**
55
+ ```plaintext
56
+ gradio
57
+ librosa
58
+ resemblyzer
59
+ numpy
60
+ soundfile
61
+ ```
62
+
63
+ ---
64
+
65
+ ## 🧠 **How It Works**
66
+ 1. **Audio Loading:** Files are loaded and resampled to **16 kHz**.
67
+ 2. **Voice Embeddings:** The **Resemblyzer** extracts embeddings that represent vocal characteristics.
68
+ 3. **Similarity Calculation:** The dot product of normalized embeddings produces the similarity score.
69
+
70
+ ---
71
+
72
+ ## 🌐 **Access Live Demo**
73
+ πŸ”— [wave-app](https://huggingface.co/spaces/ajnx014/voice-recognition-app)
74
+
75
+ ---
76
+
77
+ ## πŸ“ **License**
78
+ This project is licensed under the **MIT License**.
79
+
80
+ ---
81
+
82
+ ## 🀝 **Contributing**
83
+ Feel free to contribute! Fork the repository, create a new branch, and submit a pull request.
84
+
85
+ ---
86
+
87
+ ## πŸ“§ **Contact**
88
+ For inquiries or support, please reach out to **[arjunjagdale14@gmail.com](mailto:arjunjagdale14@gmail.com)**.
89
+
90
+ ---
91
+
92
+ > **Author:** Arjun Jagdale
93
+ > **GitHub:** [ArjunJagdale](https://github.com/ArjunJagdale)
94
+ > **Project:** Voice Recognition with Similarity Testing
95
+