audio-scribe 0.1.4__tar.gz → 0.1.6__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.
- {audio_scribe-0.1.4/src/audio_scribe.egg-info → audio_scribe-0.1.6}/PKG-INFO +100 -27
- audio_scribe-0.1.4/PKG-INFO → audio_scribe-0.1.6/README.md +89 -64
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/setup.py +16 -11
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe/__init__.py +6 -6
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe/models.py +2 -2
- audio_scribe-0.1.6/src/audio_scribe/transcriber.py +373 -0
- audio_scribe-0.1.4/README.md → audio_scribe-0.1.6/src/audio_scribe.egg-info/PKG-INFO +137 -17
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe.egg-info/entry_points.txt +1 -0
- audio_scribe-0.1.6/src/audio_scribe.egg-info/requires.txt +9 -0
- audio_scribe-0.1.6/tests/test_transcriber.py +469 -0
- audio_scribe-0.1.4/src/audio_scribe/transcriber.py +0 -135
- audio_scribe-0.1.4/src/audio_scribe.egg-info/requires.txt +0 -9
- audio_scribe-0.1.4/tests/test_transcriber.py +0 -188
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/LICENSE +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/setup.cfg +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe/auth.py +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe/config.py +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe/utils.py +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe.egg-info/SOURCES.txt +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe.egg-info/dependency_links.txt +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/src/audio_scribe.egg-info/top_level.txt +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/tests/test_auth.py +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/tests/test_config.py +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/tests/test_models.py +0 -0
- {audio_scribe-0.1.4 → audio_scribe-0.1.6}/tests/test_utils.py +0 -0
@@ -1,13 +1,13 @@
|
|
1
|
-
Metadata-Version: 2.
|
1
|
+
Metadata-Version: 2.4
|
2
2
|
Name: audio_scribe
|
3
|
-
Version: 0.1.
|
3
|
+
Version: 0.1.6
|
4
4
|
Summary: A command-line tool for audio transcription with Whisper and Pyannote.
|
5
|
-
Home-page: https://gitlab.genomicops.cloud/
|
5
|
+
Home-page: https://gitlab.genomicops.cloud/innovation-hub/audio-scribe
|
6
6
|
Author: Gurasis Osahan
|
7
7
|
Author-email: contact@genomicops.com
|
8
8
|
License: Apache-2.0
|
9
|
-
Project-URL: Source, https://gitlab.genomicops.cloud/
|
10
|
-
Project-URL: Tracker, https://gitlab.genomicops.cloud/
|
9
|
+
Project-URL: Source, https://gitlab.genomicops.cloud/innovation-hub/audio-scribe
|
10
|
+
Project-URL: Tracker, https://gitlab.genomicops.cloud/innovation-hub/audio-scribe/-/issues
|
11
11
|
Keywords: whisper pyannote transcription audio diarization
|
12
12
|
Classifier: Development Status :: 3 - Alpha
|
13
13
|
Classifier: Intended Audience :: Developers
|
@@ -23,15 +23,15 @@ Classifier: Operating System :: OS Independent
|
|
23
23
|
Requires-Python: >=3.8
|
24
24
|
Description-Content-Type: text/markdown
|
25
25
|
License-File: LICENSE
|
26
|
-
Requires-Dist: torch
|
26
|
+
Requires-Dist: torch>=2.7.1
|
27
27
|
Requires-Dist: openai-whisper
|
28
|
-
Requires-Dist: pyannote.audio
|
28
|
+
Requires-Dist: pyannote.audio>=3.3.2
|
29
29
|
Requires-Dist: pytorch-lightning
|
30
|
-
Requires-Dist: keyring
|
30
|
+
Requires-Dist: keyring>=25.6.0
|
31
31
|
Requires-Dist: cryptography
|
32
|
-
Requires-Dist: alive-progress
|
33
|
-
Requires-Dist: psutil
|
34
|
-
Requires-Dist: GPUtil
|
32
|
+
Requires-Dist: alive-progress>=3.2.0
|
33
|
+
Requires-Dist: psutil>=7.0.0
|
34
|
+
Requires-Dist: GPUtil>=1.4.0
|
35
35
|
Dynamic: author
|
36
36
|
Dynamic: author-email
|
37
37
|
Dynamic: classifier
|
@@ -40,6 +40,7 @@ Dynamic: description-content-type
|
|
40
40
|
Dynamic: home-page
|
41
41
|
Dynamic: keywords
|
42
42
|
Dynamic: license
|
43
|
+
Dynamic: license-file
|
43
44
|
Dynamic: project-url
|
44
45
|
Dynamic: requires-dist
|
45
46
|
Dynamic: requires-python
|
@@ -52,7 +53,7 @@ Dynamic: summary
|
|
52
53
|
|
53
54
|
<p align="center" style="margin: 0px auto;">
|
54
55
|
<img src="https://img.shields.io/gitlab/pipeline-status/innovation-hub%2Faudio-scribe?gitlab_url=https%3A%2F%2Fgitlab.genomicops.cloud&style=for-the-badge&logo=gitlab&logoColor=white&color=green" alt="Pipeline Status">
|
55
|
-
<img src="https://img.shields.io/gitlab/pipeline-coverage/innovation-hub%2Faudio-scribe?gitlab_url=https%3A%2F%2Fgitlab.genomicops.cloud&style=for-the-badge&logo=tag&logoColor=white&color=red" alt="Coverage">
|
56
|
+
<img src="https://img.shields.io/gitlab/pipeline-coverage/innovation-hub%2Faudio-scribe?gitlab_url=https%3A%2F%2Fgitlab.genomicops.cloud&branch=main&style=for-the-badge&logo=tag&logoColor=white&color=red" alt="Coverage">
|
56
57
|
<img src="https://img.shields.io/pypi/pyversions/audio-scribe?style=for-the-badge&logo=python&logoColor=white&logoWidth=30&color=yellow" alt="Python Versions">
|
57
58
|
<img src="https://img.shields.io/pypi/dm/audio-scribe?style=for-the-badge&logo=pypi&logoColor=white&logoWidth=30&color=orange" alt="PyPI Downloads">
|
58
59
|
<img src="https://img.shields.io/gitlab/v/tag/innovation-hub%2Faudio-scribe?gitlab_url=https%3A%2F%2Fgitlab.genomicops.cloud&style=for-the-badge&logo=tag&logoColor=white&color=red" alt="Version">
|
@@ -67,9 +68,9 @@ Dynamic: summary
|
|
67
68
|
|
68
69
|
## Support the Project ☕
|
69
70
|
|
70
|
-
<p align="center">
|
71
|
-
<a href="https://
|
72
|
-
<img src="https://
|
71
|
+
<p align="center" style="margin: 0px auto;">
|
72
|
+
<a href="https://buymeacoffee.com/gosahan" target="_blank">
|
73
|
+
<img src="https://img.shields.io/badge/Buy%20Me%20A%20Coffee-Support-yellow?style=for-the-badge&logo=buymeacoffee&logoColor=white" alt="Buy Me A Coffee Badge"/>
|
73
74
|
</a>
|
74
75
|
</p>
|
75
76
|
|
@@ -107,11 +108,13 @@ This repository is licensed under the [Apache License 2.0](#license).
|
|
107
108
|
- [Usage](#usage)
|
108
109
|
- [Dependencies](#dependencies)
|
109
110
|
- [Sample `requirements.txt`](#sample-requirementstxt)
|
111
|
+
- [Troubleshooting](#troubleshooting)
|
112
|
+
- [IndexError: list index out of range](#indexerror-list-index-out-of-range)
|
113
|
+
- [Option 1: System-level Installation (requires sudo access)](#option-1-system-level-installation-requires-sudo-access)
|
114
|
+
- [Option 2: Conda-only Installation (no sudo required)](#option-2-conda-only-installation-no-sudo-required)
|
110
115
|
- [Contributing](#contributing)
|
111
116
|
- [License](#license)
|
112
117
|
|
113
|
-
---
|
114
|
-
|
115
118
|
## Features
|
116
119
|
|
117
120
|
- **Whisper Transcription**
|
@@ -127,8 +130,6 @@ This repository is licensed under the [Apache License 2.0](#license).
|
|
127
130
|
- **Configurable Models**
|
128
131
|
Default is `base.en` but you can specify any other Whisper model using `--whisper-model`.
|
129
132
|
|
130
|
-
---
|
131
|
-
|
132
133
|
## Installation
|
133
134
|
|
134
135
|
### Installing from PyPI
|
@@ -157,8 +158,6 @@ pip install -r requirements.txt
|
|
157
158
|
|
158
159
|
This approach is particularly useful if you want the newest changes or plan to contribute.
|
159
160
|
|
160
|
-
---
|
161
|
-
|
162
161
|
## Quick Start
|
163
162
|
|
164
163
|
1. **Obtain a Hugging Face Token**
|
@@ -174,7 +173,6 @@ This approach is particularly useful if you want the newest changes or plan to c
|
|
174
173
|
3. **Watch the Progress Bar**
|
175
174
|
- The tool displays a progress bar for each diarized speaker turn, along with real-time CPU, GPU, and memory usage.
|
176
175
|
|
177
|
-
---
|
178
176
|
|
179
177
|
## Usage
|
180
178
|
|
@@ -222,7 +220,6 @@ optional arguments:
|
|
222
220
|
# When prompted for an audio file path, press Tab to autocomplete
|
223
221
|
```
|
224
222
|
|
225
|
-
---
|
226
223
|
|
227
224
|
## Dependencies
|
228
225
|
|
@@ -258,11 +255,89 @@ GPUtil
|
|
258
255
|
pyreadline3; sys_platform == "win32"
|
259
256
|
```
|
260
257
|
|
261
|
-
> Note:
|
258
|
+
> Note:
|
262
259
|
> - `pyreadline3` is appended with a [PEP 508 marker](https://peps.python.org/pep-0508/) (`; sys_platform == "win32"`) so it only installs on Windows.
|
263
260
|
> - For GPU support, ensure you install a compatible PyTorch version with CUDA.
|
264
261
|
|
265
|
-
|
262
|
+
## Troubleshooting
|
263
|
+
|
264
|
+
### IndexError: list index out of range
|
265
|
+
|
266
|
+
**Symptom**
|
267
|
+
|
268
|
+
You encounter the following error when running `audio-scribe` or importing `pyannote.audio`:
|
269
|
+
|
270
|
+
```
|
271
|
+
IndexError: list index out of range
|
272
|
+
File ".../pyannote/audio/core/io.py", line 214, in __init__
|
273
|
+
backend = "soundfile" if "soundfile" in backends else backends[0]
|
274
|
+
```
|
275
|
+
|
276
|
+
This occurs when `pyannote.audio` is unable to detect any supported audio backend. Most commonly, the `soundfile` module is missing or its dependency `libsndfile` is not properly installed.
|
277
|
+
|
278
|
+
**Solution**
|
279
|
+
|
280
|
+
You have two ways to resolve this issue:
|
281
|
+
|
282
|
+
#### Option 1: System-level Installation (requires sudo access)
|
283
|
+
|
284
|
+
Install the system-level audio backend library:
|
285
|
+
|
286
|
+
```bash
|
287
|
+
sudo apt-get update
|
288
|
+
sudo apt-get install libsndfile1
|
289
|
+
```
|
290
|
+
|
291
|
+
Then reinstall the `soundfile` Python package inside your environment:
|
292
|
+
|
293
|
+
```bash
|
294
|
+
# If using conda
|
295
|
+
conda activate your-environment-name
|
296
|
+
pip uninstall soundfile -y
|
297
|
+
pip install soundfile
|
298
|
+
|
299
|
+
# If using pip/virtualenv
|
300
|
+
source your-venv/bin/activate # or equivalent activation command
|
301
|
+
pip uninstall soundfile -y
|
302
|
+
pip install soundfile
|
303
|
+
```
|
304
|
+
|
305
|
+
#### Option 2: Conda-only Installation (no sudo required)
|
306
|
+
|
307
|
+
Inside your Conda environment:
|
308
|
+
|
309
|
+
```bash
|
310
|
+
conda activate your-environment-name
|
311
|
+
conda install -c conda-forge libsndfile
|
312
|
+
```
|
313
|
+
|
314
|
+
Then ensure Python uses the correct bindings:
|
315
|
+
|
316
|
+
```bash
|
317
|
+
pip uninstall soundfile -y
|
318
|
+
pip install soundfile
|
319
|
+
```
|
320
|
+
|
321
|
+
**Verification**
|
322
|
+
|
323
|
+
Test that audio backends are now available:
|
324
|
+
|
325
|
+
```bash
|
326
|
+
python -c "import soundfile as sf; print(sf.available_formats())"
|
327
|
+
```
|
328
|
+
|
329
|
+
Expected output:
|
330
|
+
```python
|
331
|
+
{'WAV': 'Microsoft WAV format (little endian)', 'FLAC': 'FLAC format', ...}
|
332
|
+
```
|
333
|
+
|
334
|
+
Then re-run `audio-scribe`:
|
335
|
+
|
336
|
+
```bash
|
337
|
+
audio-scribe --audio path/to/your/audio.wav
|
338
|
+
```
|
339
|
+
|
340
|
+
The tool should now initialize without error.
|
266
341
|
|
267
342
|
## Contributing
|
268
343
|
|
@@ -275,8 +350,6 @@ We welcome contributions to **Audio Scribe**!
|
|
275
350
|
|
276
351
|
Please read any available guidelines or templates in our repository (such as `CONTRIBUTING.md` or `CODE_OF_CONDUCT.md`) before submitting.
|
277
352
|
|
278
|
-
---
|
279
|
-
|
280
353
|
## License
|
281
354
|
|
282
355
|
This project is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).
|
@@ -1,50 +1,3 @@
|
|
1
|
-
Metadata-Version: 2.2
|
2
|
-
Name: audio_scribe
|
3
|
-
Version: 0.1.4
|
4
|
-
Summary: A command-line tool for audio transcription with Whisper and Pyannote.
|
5
|
-
Home-page: https://gitlab.genomicops.cloud/genomicops/audio-scribe
|
6
|
-
Author: Gurasis Osahan
|
7
|
-
Author-email: contact@genomicops.com
|
8
|
-
License: Apache-2.0
|
9
|
-
Project-URL: Source, https://gitlab.genomicops.cloud/genomicops/audio-scribe
|
10
|
-
Project-URL: Tracker, https://gitlab.genomicops.cloud/genomicops/audio-scribe/-/issues
|
11
|
-
Keywords: whisper pyannote transcription audio diarization
|
12
|
-
Classifier: Development Status :: 3 - Alpha
|
13
|
-
Classifier: Intended Audience :: Developers
|
14
|
-
Classifier: Intended Audience :: Science/Research
|
15
|
-
Classifier: Topic :: Multimedia :: Sound/Audio
|
16
|
-
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
17
|
-
Classifier: License :: OSI Approved :: Apache Software License
|
18
|
-
Classifier: Programming Language :: Python :: 3
|
19
|
-
Classifier: Programming Language :: Python :: 3.8
|
20
|
-
Classifier: Programming Language :: Python :: 3.9
|
21
|
-
Classifier: Programming Language :: Python :: 3.10
|
22
|
-
Classifier: Operating System :: OS Independent
|
23
|
-
Requires-Python: >=3.8
|
24
|
-
Description-Content-Type: text/markdown
|
25
|
-
License-File: LICENSE
|
26
|
-
Requires-Dist: torch
|
27
|
-
Requires-Dist: openai-whisper
|
28
|
-
Requires-Dist: pyannote.audio
|
29
|
-
Requires-Dist: pytorch-lightning
|
30
|
-
Requires-Dist: keyring
|
31
|
-
Requires-Dist: cryptography
|
32
|
-
Requires-Dist: alive-progress
|
33
|
-
Requires-Dist: psutil
|
34
|
-
Requires-Dist: GPUtil
|
35
|
-
Dynamic: author
|
36
|
-
Dynamic: author-email
|
37
|
-
Dynamic: classifier
|
38
|
-
Dynamic: description
|
39
|
-
Dynamic: description-content-type
|
40
|
-
Dynamic: home-page
|
41
|
-
Dynamic: keywords
|
42
|
-
Dynamic: license
|
43
|
-
Dynamic: project-url
|
44
|
-
Dynamic: requires-dist
|
45
|
-
Dynamic: requires-python
|
46
|
-
Dynamic: summary
|
47
|
-
|
48
1
|
# Audio Scribe
|
49
2
|
|
50
3
|
**A Command-Line Tool for Audio Transcription and Speaker Diarization Using OpenAI Whisper and Pyannote**
|
@@ -52,7 +5,7 @@ Dynamic: summary
|
|
52
5
|
|
53
6
|
<p align="center" style="margin: 0px auto;">
|
54
7
|
<img src="https://img.shields.io/gitlab/pipeline-status/innovation-hub%2Faudio-scribe?gitlab_url=https%3A%2F%2Fgitlab.genomicops.cloud&style=for-the-badge&logo=gitlab&logoColor=white&color=green" alt="Pipeline Status">
|
55
|
-
<img src="https://img.shields.io/gitlab/pipeline-coverage/innovation-hub%2Faudio-scribe?gitlab_url=https%3A%2F%2Fgitlab.genomicops.cloud&style=for-the-badge&logo=tag&logoColor=white&color=red" alt="Coverage">
|
8
|
+
<img src="https://img.shields.io/gitlab/pipeline-coverage/innovation-hub%2Faudio-scribe?gitlab_url=https%3A%2F%2Fgitlab.genomicops.cloud&branch=main&style=for-the-badge&logo=tag&logoColor=white&color=red" alt="Coverage">
|
56
9
|
<img src="https://img.shields.io/pypi/pyversions/audio-scribe?style=for-the-badge&logo=python&logoColor=white&logoWidth=30&color=yellow" alt="Python Versions">
|
57
10
|
<img src="https://img.shields.io/pypi/dm/audio-scribe?style=for-the-badge&logo=pypi&logoColor=white&logoWidth=30&color=orange" alt="PyPI Downloads">
|
58
11
|
<img src="https://img.shields.io/gitlab/v/tag/innovation-hub%2Faudio-scribe?gitlab_url=https%3A%2F%2Fgitlab.genomicops.cloud&style=for-the-badge&logo=tag&logoColor=white&color=red" alt="Version">
|
@@ -67,9 +20,9 @@ Dynamic: summary
|
|
67
20
|
|
68
21
|
## Support the Project ☕
|
69
22
|
|
70
|
-
<p align="center">
|
71
|
-
<a href="https://
|
72
|
-
<img src="https://
|
23
|
+
<p align="center" style="margin: 0px auto;">
|
24
|
+
<a href="https://buymeacoffee.com/gosahan" target="_blank">
|
25
|
+
<img src="https://img.shields.io/badge/Buy%20Me%20A%20Coffee-Support-yellow?style=for-the-badge&logo=buymeacoffee&logoColor=white" alt="Buy Me A Coffee Badge"/>
|
73
26
|
</a>
|
74
27
|
</p>
|
75
28
|
|
@@ -107,11 +60,13 @@ This repository is licensed under the [Apache License 2.0](#license).
|
|
107
60
|
- [Usage](#usage)
|
108
61
|
- [Dependencies](#dependencies)
|
109
62
|
- [Sample `requirements.txt`](#sample-requirementstxt)
|
63
|
+
- [Troubleshooting](#troubleshooting)
|
64
|
+
- [IndexError: list index out of range](#indexerror-list-index-out-of-range)
|
65
|
+
- [Option 1: System-level Installation (requires sudo access)](#option-1-system-level-installation-requires-sudo-access)
|
66
|
+
- [Option 2: Conda-only Installation (no sudo required)](#option-2-conda-only-installation-no-sudo-required)
|
110
67
|
- [Contributing](#contributing)
|
111
68
|
- [License](#license)
|
112
69
|
|
113
|
-
---
|
114
|
-
|
115
70
|
## Features
|
116
71
|
|
117
72
|
- **Whisper Transcription**
|
@@ -127,8 +82,6 @@ This repository is licensed under the [Apache License 2.0](#license).
|
|
127
82
|
- **Configurable Models**
|
128
83
|
Default is `base.en` but you can specify any other Whisper model using `--whisper-model`.
|
129
84
|
|
130
|
-
---
|
131
|
-
|
132
85
|
## Installation
|
133
86
|
|
134
87
|
### Installing from PyPI
|
@@ -157,8 +110,6 @@ pip install -r requirements.txt
|
|
157
110
|
|
158
111
|
This approach is particularly useful if you want the newest changes or plan to contribute.
|
159
112
|
|
160
|
-
---
|
161
|
-
|
162
113
|
## Quick Start
|
163
114
|
|
164
115
|
1. **Obtain a Hugging Face Token**
|
@@ -174,7 +125,6 @@ This approach is particularly useful if you want the newest changes or plan to c
|
|
174
125
|
3. **Watch the Progress Bar**
|
175
126
|
- The tool displays a progress bar for each diarized speaker turn, along with real-time CPU, GPU, and memory usage.
|
176
127
|
|
177
|
-
---
|
178
128
|
|
179
129
|
## Usage
|
180
130
|
|
@@ -222,7 +172,6 @@ optional arguments:
|
|
222
172
|
# When prompted for an audio file path, press Tab to autocomplete
|
223
173
|
```
|
224
174
|
|
225
|
-
---
|
226
175
|
|
227
176
|
## Dependencies
|
228
177
|
|
@@ -258,11 +207,89 @@ GPUtil
|
|
258
207
|
pyreadline3; sys_platform == "win32"
|
259
208
|
```
|
260
209
|
|
261
|
-
> Note:
|
210
|
+
> Note:
|
262
211
|
> - `pyreadline3` is appended with a [PEP 508 marker](https://peps.python.org/pep-0508/) (`; sys_platform == "win32"`) so it only installs on Windows.
|
263
212
|
> - For GPU support, ensure you install a compatible PyTorch version with CUDA.
|
264
213
|
|
265
|
-
|
214
|
+
## Troubleshooting
|
215
|
+
|
216
|
+
### IndexError: list index out of range
|
217
|
+
|
218
|
+
**Symptom**
|
219
|
+
|
220
|
+
You encounter the following error when running `audio-scribe` or importing `pyannote.audio`:
|
221
|
+
|
222
|
+
```
|
223
|
+
IndexError: list index out of range
|
224
|
+
File ".../pyannote/audio/core/io.py", line 214, in __init__
|
225
|
+
backend = "soundfile" if "soundfile" in backends else backends[0]
|
226
|
+
```
|
227
|
+
|
228
|
+
This occurs when `pyannote.audio` is unable to detect any supported audio backend. Most commonly, the `soundfile` module is missing or its dependency `libsndfile` is not properly installed.
|
229
|
+
|
230
|
+
**Solution**
|
231
|
+
|
232
|
+
You have two ways to resolve this issue:
|
233
|
+
|
234
|
+
#### Option 1: System-level Installation (requires sudo access)
|
235
|
+
|
236
|
+
Install the system-level audio backend library:
|
237
|
+
|
238
|
+
```bash
|
239
|
+
sudo apt-get update
|
240
|
+
sudo apt-get install libsndfile1
|
241
|
+
```
|
242
|
+
|
243
|
+
Then reinstall the `soundfile` Python package inside your environment:
|
244
|
+
|
245
|
+
```bash
|
246
|
+
# If using conda
|
247
|
+
conda activate your-environment-name
|
248
|
+
pip uninstall soundfile -y
|
249
|
+
pip install soundfile
|
250
|
+
|
251
|
+
# If using pip/virtualenv
|
252
|
+
source your-venv/bin/activate # or equivalent activation command
|
253
|
+
pip uninstall soundfile -y
|
254
|
+
pip install soundfile
|
255
|
+
```
|
256
|
+
|
257
|
+
#### Option 2: Conda-only Installation (no sudo required)
|
258
|
+
|
259
|
+
Inside your Conda environment:
|
260
|
+
|
261
|
+
```bash
|
262
|
+
conda activate your-environment-name
|
263
|
+
conda install -c conda-forge libsndfile
|
264
|
+
```
|
265
|
+
|
266
|
+
Then ensure Python uses the correct bindings:
|
267
|
+
|
268
|
+
```bash
|
269
|
+
pip uninstall soundfile -y
|
270
|
+
pip install soundfile
|
271
|
+
```
|
272
|
+
|
273
|
+
**Verification**
|
274
|
+
|
275
|
+
Test that audio backends are now available:
|
276
|
+
|
277
|
+
```bash
|
278
|
+
python -c "import soundfile as sf; print(sf.available_formats())"
|
279
|
+
```
|
280
|
+
|
281
|
+
Expected output:
|
282
|
+
```python
|
283
|
+
{'WAV': 'Microsoft WAV format (little endian)', 'FLAC': 'FLAC format', ...}
|
284
|
+
```
|
285
|
+
|
286
|
+
Then re-run `audio-scribe`:
|
287
|
+
|
288
|
+
```bash
|
289
|
+
audio-scribe --audio path/to/your/audio.wav
|
290
|
+
```
|
291
|
+
|
292
|
+
The tool should now initialize without error.
|
266
293
|
|
267
294
|
## Contributing
|
268
295
|
|
@@ -275,8 +302,6 @@ We welcome contributions to **Audio Scribe**!
|
|
275
302
|
|
276
303
|
Please read any available guidelines or templates in our repository (such as `CONTRIBUTING.md` or `CODE_OF_CONDUCT.md`) before submitting.
|
277
304
|
|
278
|
-
---
|
279
|
-
|
280
305
|
## License
|
281
306
|
|
282
307
|
This project is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).
|
@@ -300,4 +325,4 @@ limitations under the License.
|
|
300
325
|
---
|
301
326
|
|
302
327
|
**Thank you for using Audio Scribe!**
|
303
|
-
For questions or feedback, please open a [GitHub issue](https://gitlab.genomicops.cloud/innovation-hub/audio-scribe/-/issues) or contact the maintainers.
|
328
|
+
For questions or feedback, please open a [GitHub issue](https://gitlab.genomicops.cloud/innovation-hub/audio-scribe/-/issues) or contact the maintainers.
|
@@ -5,33 +5,38 @@ with open("README.md", "r", encoding="utf-8") as fh:
|
|
5
5
|
|
6
6
|
setuptools.setup(
|
7
7
|
name="audio_scribe",
|
8
|
-
version="0.1.
|
8
|
+
version="0.1.6",
|
9
9
|
author="Gurasis Osahan",
|
10
10
|
author_email="contact@genomicops.com",
|
11
11
|
description="A command-line tool for audio transcription with Whisper and Pyannote.",
|
12
12
|
long_description=long_description,
|
13
13
|
long_description_content_type="text/markdown",
|
14
|
-
url="https://gitlab.genomicops.cloud/
|
14
|
+
url="https://gitlab.genomicops.cloud/innovation-hub/audio-scribe",
|
15
15
|
package_dir={"": "src"},
|
16
16
|
packages=setuptools.find_packages(where="src"),
|
17
17
|
python_requires=">=3.8",
|
18
18
|
install_requires=[
|
19
|
-
"torch",
|
19
|
+
"torch>=2.7.1",
|
20
20
|
"openai-whisper",
|
21
|
-
"pyannote.audio",
|
21
|
+
"pyannote.audio>=3.3.2",
|
22
22
|
"pytorch-lightning",
|
23
|
-
"keyring",
|
23
|
+
"keyring>=25.6.0",
|
24
24
|
"cryptography",
|
25
|
-
"alive-progress",
|
26
|
-
"psutil",
|
27
|
-
"GPUtil",
|
25
|
+
"alive-progress>=3.2.0",
|
26
|
+
"psutil>=7.0.0",
|
27
|
+
"GPUtil>=1.4.0",
|
28
28
|
],
|
29
|
-
entry_points={
|
29
|
+
entry_points={
|
30
|
+
"console_scripts": [
|
31
|
+
"audio-scribe=audio_scribe.transcriber:main",
|
32
|
+
"audioscribe=audio_scribe.transcriber:main",
|
33
|
+
]
|
34
|
+
},
|
30
35
|
keywords="whisper pyannote transcription audio diarization",
|
31
36
|
license="Apache-2.0",
|
32
37
|
project_urls={
|
33
|
-
"Source": "https://gitlab.genomicops.cloud/
|
34
|
-
"Tracker": "https://gitlab.genomicops.cloud/
|
38
|
+
"Source": "https://gitlab.genomicops.cloud/innovation-hub/audio-scribe",
|
39
|
+
"Tracker": "https://gitlab.genomicops.cloud/innovation-hub/audio-scribe/-/issues",
|
35
40
|
},
|
36
41
|
classifiers=[
|
37
42
|
"Development Status :: 3 - Alpha",
|
@@ -5,13 +5,13 @@ A Python package for transcribing audio files with speaker diarization
|
|
5
5
|
using Whisper and Pyannote.
|
6
6
|
"""
|
7
7
|
|
8
|
-
from .transcriber import main
|
9
|
-
from .models import TranscriptionPipeline, AudioProcessor
|
10
|
-
from .config import TranscriptionConfig
|
11
|
-
from .auth import TokenManager
|
12
|
-
from .utils import DependencyManager, complete_path
|
8
|
+
from audio_scribe.transcriber import main
|
9
|
+
from audio_scribe.models import TranscriptionPipeline, AudioProcessor
|
10
|
+
from audio_scribe.config import TranscriptionConfig
|
11
|
+
from audio_scribe.auth import TokenManager
|
12
|
+
from audio_scribe.utils import DependencyManager, complete_path
|
13
13
|
|
14
|
-
__version__ = "0.1.
|
14
|
+
__version__ = "0.1.6"
|
15
15
|
|
16
16
|
__all__ = [
|
17
17
|
"main",
|
@@ -11,8 +11,8 @@ from datetime import datetime
|
|
11
11
|
from pathlib import Path
|
12
12
|
from pyannote.audio import Pipeline # type: ignore
|
13
13
|
|
14
|
-
from .config import TranscriptionConfig
|
15
|
-
from .auth import TokenManager
|
14
|
+
from audio_scribe.config import TranscriptionConfig
|
15
|
+
from audio_scribe.auth import TokenManager
|
16
16
|
|
17
17
|
logger = logging.getLogger(__name__)
|
18
18
|
|