speaker-detector 0.1.3__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (20) hide show
  1. speaker_detector-0.1.3/PKG-INFO +101 -0
  2. speaker_detector-0.1.3/README.md +75 -0
  3. speaker_detector-0.1.3/pyproject.toml +50 -0
  4. speaker_detector-0.1.3/setup.cfg +4 -0
  5. speaker_detector-0.1.3/speaker_detector/ECAPA_TDNN.py +633 -0
  6. speaker_detector-0.1.3/speaker_detector/__init__.py +0 -0
  7. speaker_detector-0.1.3/speaker_detector/__main__.py +4 -0
  8. speaker_detector-0.1.3/speaker_detector/analyze.py +59 -0
  9. speaker_detector-0.1.3/speaker_detector/cli.py +82 -0
  10. speaker_detector-0.1.3/speaker_detector/combine.py +22 -0
  11. speaker_detector-0.1.3/speaker_detector/core.py +103 -0
  12. speaker_detector-0.1.3/speaker_detector/export_embeddings.py +41 -0
  13. speaker_detector-0.1.3/speaker_detector/export_model.py +40 -0
  14. speaker_detector-0.1.3/speaker_detector/generate_summary.py +110 -0
  15. speaker_detector-0.1.3/speaker_detector.egg-info/PKG-INFO +101 -0
  16. speaker_detector-0.1.3/speaker_detector.egg-info/SOURCES.txt +18 -0
  17. speaker_detector-0.1.3/speaker_detector.egg-info/dependency_links.txt +1 -0
  18. speaker_detector-0.1.3/speaker_detector.egg-info/entry_points.txt +2 -0
  19. speaker_detector-0.1.3/speaker_detector.egg-info/requires.txt +4 -0
  20. speaker_detector-0.1.3/speaker_detector.egg-info/top_level.txt +1 -0
speaker_detector-0.1.3/PKG-INFO ADDED
@@ -0,0 +1,101 @@
1
+ Metadata-Version: 2.4
2
+ Name: speaker-detector
3
+ Version: 0.1.3
4
+ Summary: A CLI tool for speaker enrollment and identification using SpeechBrain.
5
+ Author-email: Lara Whybrow <lara.whybrow@gmail.com>
6
+ License: MIT
7
+ Project-URL: Homepage, https://github.com/P0llen/speaker-detector
8
+ Project-URL: Repository, https://github.com/P0llen/speaker-detector
9
+ Project-URL: Issues, https://github.com/P0llen/speaker-detector/issues
10
+ Project-URL: Documentation, https://github.com/P0llen/speaker-detector#readme
11
+ Keywords: speaker-recognition,speechbrain,voice,cli,ai
12
+ Classifier: Development Status :: 3 - Alpha
13
+ Classifier: Intended Audience :: Developers
14
+ Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
15
+ Classifier: License :: OSI Approved :: MIT License
16
+ Classifier: Programming Language :: Python :: 3
17
+ Classifier: Programming Language :: Python :: 3.8
18
+ Classifier: Programming Language :: Python :: 3.9
19
+ Classifier: Programming Language :: Python :: 3.10
20
+ Requires-Python: >=3.8
21
+ Description-Content-Type: text/markdown
22
+ Requires-Dist: torch
23
+ Requires-Dist: torchaudio
24
+ Requires-Dist: speechbrain
25
+ Requires-Dist: onnx
26
+
27
+ # speaker-detector ๐ŸŽ™๏ธ
28
+
29
+ A lightweight CLI tool for speaker enrollment and voice identification, powered by [SpeechBrain](https://speechbrain.readthedocs.io/).
30
+
31
+ ## ๐Ÿ”ง Features
32
+
33
+
34
+ - โœ… Enroll speakers from .wav audio
35
+ - ๐Ÿ•ต๏ธ Identify speakers from audio samples
36
+ - ๐Ÿง  ECAPA-TDNN embedding-based matching
37
+ - ๐ŸŽ›๏ธ Simple, fast command-line interface
38
+ - ๐Ÿ“ Clean file storage in `~/.speaker-detector/`
39
+ - ๐Ÿ”Š Optional `--verbose` mode for debugging
40
+
41
+
42
+ ## ๐Ÿ“ฆ Installation
43
+
44
+ Install from [TestPyPI](https://test.pypi.org/):
45
+
46
+ ```bash
47
+ pip install --index-url https://test.pypi.org/simple/ speaker-detector
48
+ ```
49
+
50
+ ## ๐Ÿš€ Usage
51
+
52
+ ## ๐ŸŽ™๏ธ Enroll a speaker:
53
+
54
+ ```bash
55
+ speaker-detector record --enroll Lara
56
+ ```
57
+
58
+ ## ๐Ÿ•ต๏ธ Identify a speaker:
59
+
60
+ ```bash
61
+ speaker-detector record --test
62
+ ```
63
+ ## ๐Ÿ“‹ List enrolled speakers:
64
+
65
+ ```bash
66
+ speaker-detector list
67
+ ```
68
+
69
+ ## ๐Ÿ—‚๏ธ Project Structure
70
+
71
+ ~/.speaker-detector/enrollments/ Saved .pt voice embeddings
72
+ ~/.speaker-detector/recordings/ CLI-recorded .wav audio files
73
+
74
+ ๐Ÿงน Clean vs Verbose Mode
75
+ By default, warnings from speechbrain, torch, etc. are hidden for a clean CLI experience.
76
+ To enable full logs & deprecation warnings:
77
+
78
+ speaker-detector --verbose identify samples/test_sample.wav
79
+
80
+ ๐Ÿ›  Requirements
81
+ Python 3.8+
82
+ torch
83
+ speechbrain
84
+ numpy
85
+ soundfile
86
+ onnxruntime
87
+
88
+ | Step | Command | When / Purpose | Output |
89
+ | --------------------------------- | ------------------------------------------------------------------------------------------------------------------- | ----------------------------- | ---------------------------------------- |
90
+ | **1. Export ECAPA Model to ONNX** | `speaker-detector export-model --pt models/embedding_model.ckpt --out ecapa_model.onnx` | Run once unless model changes | `ecapa_model.onnx` |
91
+ | **2. Enroll Speaker** | `speaker-detector enroll <speaker_id> <audio_path>`<br>Example:<br>`speaker-detector enroll Lara samples/lara1.wav` | Run per new speaker | Individual `.pt` files (e.g., `Lara.pt`) |
92
+ | **3. Combine Embeddings** | `speaker-detector combine --folder data/embeddings/ --out data/enrolled_speakers.pt` | After enrolling speakers | `enrolled_speakers.pt` |
93
+ | **4. Export Speakers to JSON** | `speaker-detector export-speaker-json --pt data/enrolled_speakers.pt --out public/speakers.json` | For frontend use | `speakers.json` |
94
+ | **5. Identify Speaker** | `speaker-detector identify samples/test_sample.wav` | Identify speaker from audio | Console output: name + score |
95
+ | **6. List Enrolled Speakers** | `speaker-detector list-speakers` | Show all enrolled speakers | Console output: list of IDs |
96
+ | **Verbose Mode (optional)** | Add `--verbose` to any command:<br>`speaker-detector --verbose identify samples/test_sample.wav` | Show warnings, detailed logs | Developer debug info |
97
+
98
+
99
+
100
+
101
+ NB: When pushing to Github, do not include any .identifier files.
speaker_detector-0.1.3/README.md ADDED
@@ -0,0 +1,75 @@
1
+ # speaker-detector ๐ŸŽ™๏ธ
2
+
3
+ A lightweight CLI tool for speaker enrollment and voice identification, powered by [SpeechBrain](https://speechbrain.readthedocs.io/).
4
+
5
+ ## ๐Ÿ”ง Features
6
+
7
+
8
+ - โœ… Enroll speakers from .wav audio
9
+ - ๐Ÿ•ต๏ธ Identify speakers from audio samples
10
+ - ๐Ÿง  ECAPA-TDNN embedding-based matching
11
+ - ๐ŸŽ›๏ธ Simple, fast command-line interface
12
+ - ๐Ÿ“ Clean file storage in `~/.speaker-detector/`
13
+ - ๐Ÿ”Š Optional `--verbose` mode for debugging
14
+
15
+
16
+ ## ๐Ÿ“ฆ Installation
17
+
18
+ Install from [TestPyPI](https://test.pypi.org/):
19
+
20
+ ```bash
21
+ pip install --index-url https://test.pypi.org/simple/ speaker-detector
22
+ ```
23
+
24
+ ## ๐Ÿš€ Usage
25
+
26
+ ## ๐ŸŽ™๏ธ Enroll a speaker:
27
+
28
+ ```bash
29
+ speaker-detector record --enroll Lara
30
+ ```
31
+
32
+ ## ๐Ÿ•ต๏ธ Identify a speaker:
33
+
34
+ ```bash
35
+ speaker-detector record --test
36
+ ```
37
+ ## ๐Ÿ“‹ List enrolled speakers:
38
+
39
+ ```bash
40
+ speaker-detector list
41
+ ```
42
+
43
+ ## ๐Ÿ—‚๏ธ Project Structure
44
+
45
+ ~/.speaker-detector/enrollments/ Saved .pt voice embeddings
46
+ ~/.speaker-detector/recordings/ CLI-recorded .wav audio files
47
+
48
+ ๐Ÿงน Clean vs Verbose Mode
49
+ By default, warnings from speechbrain, torch, etc. are hidden for a clean CLI experience.
50
+ To enable full logs & deprecation warnings:
51
+
52
+ speaker-detector --verbose identify samples/test_sample.wav
53
+
54
+ ๐Ÿ›  Requirements
55
+ Python 3.8+
56
+ torch
57
+ speechbrain
58
+ numpy
59
+ soundfile
60
+ onnxruntime
61
+
62
+ | Step | Command | When / Purpose | Output |
63
+ | --------------------------------- | ------------------------------------------------------------------------------------------------------------------- | ----------------------------- | ---------------------------------------- |
64
+ | **1. Export ECAPA Model to ONNX** | `speaker-detector export-model --pt models/embedding_model.ckpt --out ecapa_model.onnx` | Run once unless model changes | `ecapa_model.onnx` |
65
+ | **2. Enroll Speaker** | `speaker-detector enroll <speaker_id> <audio_path>`<br>Example:<br>`speaker-detector enroll Lara samples/lara1.wav` | Run per new speaker | Individual `.pt` files (e.g., `Lara.pt`) |
66
+ | **3. Combine Embeddings** | `speaker-detector combine --folder data/embeddings/ --out data/enrolled_speakers.pt` | After enrolling speakers | `enrolled_speakers.pt` |
67
+ | **4. Export Speakers to JSON** | `speaker-detector export-speaker-json --pt data/enrolled_speakers.pt --out public/speakers.json` | For frontend use | `speakers.json` |
68
+ | **5. Identify Speaker** | `speaker-detector identify samples/test_sample.wav` | Identify speaker from audio | Console output: name + score |
69
+ | **6. List Enrolled Speakers** | `speaker-detector list-speakers` | Show all enrolled speakers | Console output: list of IDs |
70
+ | **Verbose Mode (optional)** | Add `--verbose` to any command:<br>`speaker-detector --verbose identify samples/test_sample.wav` | Show warnings, detailed logs | Developer debug info |
71
+
72
+
73
+
74
+
75
+ NB: When pushing to Github, do not include any .identifier files.
speaker_detector-0.1.3/pyproject.toml ADDED
@@ -0,0 +1,50 @@
1
+ [build-system]
2
+ requires = ["setuptools>=61.0", "wheel"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "speaker-detector"
7
+ version = "0.1.3"
8
+ description = "A CLI tool for speaker enrollment and identification using SpeechBrain."
9
+ readme = "README.md"
10
+ requires-python = ">=3.8"
11
+ license = { text = "MIT" }
12
+
13
+ authors = [
14
+ { name = "Lara Whybrow", email = "lara.whybrow@gmail.com" }
15
+ ]
16
+
17
+ classifiers = [
18
+ "Development Status :: 3 - Alpha",
19
+ "Intended Audience :: Developers",
20
+ "Topic :: Multimedia :: Sound/Audio :: Speech",
21
+ "License :: OSI Approved :: MIT License",
22
+ "Programming Language :: Python :: 3",
23
+ "Programming Language :: Python :: 3.8",
24
+ "Programming Language :: Python :: 3.9",
25
+ "Programming Language :: Python :: 3.10"
26
+ ]
27
+
28
+ keywords = ["speaker-recognition", "speechbrain", "voice", "cli", "ai"]
29
+
30
+ dependencies = [
31
+ "torch",
32
+ "torchaudio",
33
+ "speechbrain",
34
+ "onnx"
35
+ ]
36
+
37
+ [project.scripts]
38
+ speaker-detector = "speaker_detector.cli:main"
39
+
40
+ [project.urls]
41
+ Homepage = "https://github.com/P0llen/speaker-detector"
42
+ Repository = "https://github.com/P0llen/speaker-detector"
43
+ Issues = "https://github.com/P0llen/speaker-detector/issues"
44
+ Documentation = "https://github.com/P0llen/speaker-detector#readme"
45
+
46
+ [tool.setuptools]
47
+ packages = ["speaker_detector"]
48
+
49
+ [tool.setuptools.package-data]
50
+ speaker_detector = ["*.onnx", "*.json", "*.yaml", "models/*"]
speaker_detector-0.1.3/setup.cfg ADDED
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+