whisply 0.3__tar.gz

whisply-0.3/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

whisply-0.3/PKG-INFO

@@ -0,0 +1,226 @@
+Metadata-Version: 2.1
+Name: whisply
+Version: 0.3
+Summary: Transcribe, translate, annotate and subtitle audio and video files with OpenAI's Whisper ... fast!
+Home-page: https://github.com/tsmdt/whisply
+Author: Thomas Schmidt, Renat Shigapov
+License: Apache-2.0
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: typer==0.12.5
+Requires-Dist: faster-whisper==1.0.1
+Requires-Dist: ffmpeg-python==0.2.0
+Requires-Dist: optimum==1.19.1
+Requires-Dist: pyannote.audio==3.1.1
+Requires-Dist: pyannote.core==5.0.0
+Requires-Dist: pyannote.database==5.1.0
+Requires-Dist: pyannote.metrics==3.2.1
+Requires-Dist: pyannote.pipeline==3.0.1
+Requires-Dist: rich==13.7.1
+Requires-Dist: torch==2.3.0
+Requires-Dist: torch-audiomentations==0.11.1
+Requires-Dist: torch-pitch-shift==1.2.4
+Requires-Dist: torchaudio==2.3.0
+Requires-Dist: torchmetrics==1.3.2
+Requires-Dist: transformers==4.39.3
+Requires-Dist: validators==0.28.1
+Requires-Dist: yt-dlp>=2024.07.07
+Requires-Dist: whisperx==3.1.5
+
+# whisply
+
+<img src="https://github.com/user-attachments/assets/3a15509b-b60e-4581-af87-ecaa8e5089a3" width="25%">
+
+*Transcribe, translate, annotate and subtitle audio and video files with OpenAI's [Whisper](https://github.com/openai/whisper) ... fast!*
+
+`whisply` combines [faster-whisper](https://github.com/SYSTRAN/faster-whisper) and [insanely-fast-whisper](https://github.com/chenxwh/insanely-fast-whisper) to offer an easy-to-use solution for batch processing files. It also enables word-level speaker annotation by integrating [whisperX](https://github.com/m-bain/whisperX) and [pyannote](https://github.com/pyannote/pyannote-audio).
+
+## Table of contents
+
+- [Features](#features)
+- [Requirements](#requirements)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [Speaker annotation and diarization](#speaker-annotation-and-diarization)
+    - [Requirements](#requirements-1)
+    - [How speaker annotation works](#how-speaker-annotation-works)
+  - [Batch processing](#batch-processing)
+    - [Using config files for batch processing](#using-config-files-for-batch-processing)
+
+## Features
+
+* 🚴‍♂️ **Performance**: Depending on your hardware `whisply` will use the fastest `Whisper` implementation:
+  * CPU: `fast-whisper` or `whisperX`
+  * GPU (Nvidia CUDA) and MPS (Metal Performance Shaders, Apple M1-M3): `insanely-fast-whisper` or `whisperX`
+
+* ✅ **Auto device selection**: When performing transcription or translation tasks without speaker annotation or subtitling, `faster-whisper` (CPU) or `insanely-fast-whisper` (MPS, Nvidia GPUs) will be selected automatically based on your hardware if you do not provide a device by using the `--device` option.
+
+* 🗣️ **Word-level annotations**: If you choose to `--subtitle` or `--annotate`, `whisperX` will be used, which supports word-level segmentation and speaker annotations. Depending on your hardware, `whisperX` can run either on CPU or Nvidia GPU (but not on Apple MPS). Out of the box `whisperX` will not provide timestamps for words containing only numbers (e.g. "1.5" or "2024"): `whisply` fixes those instances through timestamp approximation.
+
+* 💬 **Subtitles**: Generating subtitles is customizable. You can specify the number of words per subtitle block (e.g., choosing "5" will generate `.srt` and `.webvtt` files where each subtitle block exactly 5 words per segment with the corresponding timestamps).
+
+* 🧺 **Batch processing**: `whisply` can process single files, whole folders, URLs or a combination of all by combining paths in a `.list` document. See the [Batch processing](#batch-processing) section for more information.
+
+* ⚙️ **Supported output formats**: `.json` `.txt` `.txt (annotated)` `.srt` `.webvtt` `.vtt` `.rttm`
+
+## Requirements
+
+* [FFmpeg](https://ffmpeg.org/)
+* \>= Python3.10
+* GPU  processing requires:
+  * Nvidia GPU (CUDA: cuBLAS and cuDNN 8 for CUDA 12) 
+  * Apple Metal Performance Shaders (MPS) (Mac M1-M3)
+* Speaker annotation requires a [HuggingFace Access Token](https://huggingface.co/docs/hub/security-tokens)
+
+<details>
+<summary><b>GPU Fix</b> for <i>Could not load library libcudnn_ops_infer.so.8.</i> (<b>click to expand</b>)</summary>
+<br>If you use <b>whisply</b> on a Linux system with a Nivida GPU and get this error:<br><br>
+
+```shell
+"Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory"
+```
+
+Run the following line in your CLI:
+
+```shell
+export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
+```
+
+Add this line to your Python environment to make it permanent:
+
+```shell
+echo "export LD_LIBRARY_PATH=\`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + \":\" + os.path.dirname(nvidia.cudnn.lib.__file__))'\`" >> path/to/your/python/env
+```
+
+For more information please refer to the <a href="https://github.com/SYSTRAN/faster-whisper" target="_blank">faster-whisper</a> GitHub page.
+
+</details>
+
+## Installation
+
+**1. Install `ffmpeg`**
+
+```markdown
+--- macOS ---
+brew install ffmpeg
+
+--- Linux ---
+sudo apt-get update
+sudo apt-get install ffmpeg
+
+--- Windows ----
+https://ffmpeg.org/download.html
+```
+
+**2. Clone this repository and change to project folder**
+
+```shell
+git clone https://github.com/tsmdt/whisply.git
+```
+
+```shell
+cd whisply
+```
+
+**3. Create a Python virtual environment**
+
+```python
+python3.11 -m venv venv
+```
+
+**4. Activate the Python virtual environment**
+
+```shell
+source venv/bin/activate
+```
+
+**5. Install `whisply` with `pip`**
+
+```python
+pip install .
+```
+
+## Usage
+
+```shell
+ Usage: whisply [OPTIONS]
+
+ WHISPLY 💬 Transcribe, translate, annotate and subtitle audio and video files with OpenAI's Whisper ... fast!
+
+╭─ Options ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+│ --files               -f       TEXT                Path to file, folder, URL or .list to process. [default: None]                                          │
+│ --output_dir          -o       DIRECTORY           Folder where transcripts should be saved. [default: transcriptions]                                     │
+│ --device              -d       [auto|cpu|gpu|mps]  Select the computation device: CPU, GPU (NVIDIA), or MPS (Mac M1-M3). [default: auto]                   │
+│ --model               -m       TEXT                Whisper model to use (List models via --list_models). [default: large-v2]                               │
+│ --lang                -l       TEXT                Language of provided file(s) ("en", "de") (Default: auto-detection). [default: None]                    │
+│ --annotate            -a                           Enable speaker annotation (Saves .rttm).                                                                │
+│ --hf_token            -hf      TEXT                HuggingFace Access token required for speaker annotation. [default: None]                               │
+│ --translate           -t                           Translate transcription to English.                                                                     │
+│ --subtitle            -s                           Create subtitles (Saves .srt, .vtt and .webvtt).                                                        │
+│ --sub_length                   INTEGER             Subtitle segment length in words [default: 5]                                                           │
+│ --verbose             -v                           Print text chunks during transcription.                                                                 │
+│ --config                       PATH                Path to configuration file. [default: None]                                                             │
+│ --list_filetypes                                   List supported audio and video file types.                                                              │
+│ --list_models                                      List available models.                                                                                  │
+│ --install-completion                               Install completion for the current shell.                                                               │
+│ --show-completion                                  Show completion for the current shell, to copy it or customize the installation.                        │
+│ --help                                             Show this message and exit.                                                                             │
+╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+  ```
+
+### Speaker annotation and diarization
+
+#### Requirements
+
+In order to annotate speakers using `--annotate` you need to provide a valid [HuggingFace](https://huggingface.co) access token using the `--hf_token` option. Additionally, you must accept the terms and conditions for both version 3.0 and version 3.1 of the `pyannote` segmentation model. For detailed instructions, refer to the *Requirements* section on the [pyannote model page on HuggingFace](https://huggingface.co/pyannote/speaker-diarization-3.1).
+
+#### How speaker annotation works
+
+`whisply` uses [whisperX](https://github.com/m-bain/whisperX) for speaker diarization and annotation. Instead of returning chunk-level timestamps like the standard `Whisper` implementation `whisperX` is able to return word-level timestamps as well as annotating speakers word by word, thus returning much more precise annotations.
+
+Out of the box `whisperX` will not provide timestamps for words containing only numbers (e.g. "1.5" or "2024"): `whisply` fixes those instances through timestamp approximation. Other known limitations of `whisperX` include:
+
+* inaccurate speaker diarization if multiple speakers talk at the same time
+* to provide word-level timestamps and annotations `whisperX` uses language specific alignment models; out of the box `whisperX` supports these languages: `en, fr, de, es, it, ja, zh, nl, uk, pt`.
+
+Refer to the [whisperX GitHub page](https://github.com/m-bain/whisperX) for more information.
+
+
+### Batch processing
+
+Instead of providing a file, folder or URL by using the `--files` option you can pass a `.list` with a mix of files, folders and URLs for processing. 
+
+Example:
+
+```shell
+$ cat my_files.list
+
+video_01.mp4
+video_02.mp4
+./my_files/
+https://youtu.be/KtOayYXEsN4?si=-0MS6KXbEWXA7dqo
+```
+
+#### Using config files for batch processing
+
+You can provide a `.json` config file by using the `--config` option which makes batch processing easy. An example config looks like this:
+
+```markdown
+{
+    "files": "./files/my_files.list",          # Path to your files
+    "output_dir": "./transcriptions",          # Output folder where transcriptions are saved
+    "device": "auto",                          # AUTO, GPU, MPS or CPU
+    "model": "large-v3-turbo",                 # Whisper model to use
+    "lang": null,                              # Null for auto-detection or language codes ("en", "de", ...)
+    "annotate": false,                         # Annotate speakers 
+    "hf_token": "HuggingFace Access Token",    # Your HuggingFace Access Token (needed for annotations)
+    "translate": false,                        # Translate to English
+    "subtitle": false,                         # Subtitle file(s)
+    "sub_length": 10,                          # Length of each subtitle block in number of words
+    "verbose": false                           # Print transcription segments while processing 
+}
+```

whisply-0.3/README.md

@@ -0,0 +1,193 @@
+# whisply
+
+<img src="https://github.com/user-attachments/assets/3a15509b-b60e-4581-af87-ecaa8e5089a3" width="25%">
+
+*Transcribe, translate, annotate and subtitle audio and video files with OpenAI's [Whisper](https://github.com/openai/whisper) ... fast!*
+
+`whisply` combines [faster-whisper](https://github.com/SYSTRAN/faster-whisper) and [insanely-fast-whisper](https://github.com/chenxwh/insanely-fast-whisper) to offer an easy-to-use solution for batch processing files. It also enables word-level speaker annotation by integrating [whisperX](https://github.com/m-bain/whisperX) and [pyannote](https://github.com/pyannote/pyannote-audio).
+
+## Table of contents
+
+- [Features](#features)
+- [Requirements](#requirements)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [Speaker annotation and diarization](#speaker-annotation-and-diarization)
+    - [Requirements](#requirements-1)
+    - [How speaker annotation works](#how-speaker-annotation-works)
+  - [Batch processing](#batch-processing)
+    - [Using config files for batch processing](#using-config-files-for-batch-processing)
+
+## Features
+
+* 🚴‍♂️ **Performance**: Depending on your hardware `whisply` will use the fastest `Whisper` implementation:
+  * CPU: `fast-whisper` or `whisperX`
+  * GPU (Nvidia CUDA) and MPS (Metal Performance Shaders, Apple M1-M3): `insanely-fast-whisper` or `whisperX`
+
+* ✅ **Auto device selection**: When performing transcription or translation tasks without speaker annotation or subtitling, `faster-whisper` (CPU) or `insanely-fast-whisper` (MPS, Nvidia GPUs) will be selected automatically based on your hardware if you do not provide a device by using the `--device` option.
+
+* 🗣️ **Word-level annotations**: If you choose to `--subtitle` or `--annotate`, `whisperX` will be used, which supports word-level segmentation and speaker annotations. Depending on your hardware, `whisperX` can run either on CPU or Nvidia GPU (but not on Apple MPS). Out of the box `whisperX` will not provide timestamps for words containing only numbers (e.g. "1.5" or "2024"): `whisply` fixes those instances through timestamp approximation.
+
+* 💬 **Subtitles**: Generating subtitles is customizable. You can specify the number of words per subtitle block (e.g., choosing "5" will generate `.srt` and `.webvtt` files where each subtitle block exactly 5 words per segment with the corresponding timestamps).
+
+* 🧺 **Batch processing**: `whisply` can process single files, whole folders, URLs or a combination of all by combining paths in a `.list` document. See the [Batch processing](#batch-processing) section for more information.
+
+* ⚙️ **Supported output formats**: `.json` `.txt` `.txt (annotated)` `.srt` `.webvtt` `.vtt` `.rttm`
+
+## Requirements
+
+* [FFmpeg](https://ffmpeg.org/)
+* \>= Python3.10
+* GPU  processing requires:
+  * Nvidia GPU (CUDA: cuBLAS and cuDNN 8 for CUDA 12) 
+  * Apple Metal Performance Shaders (MPS) (Mac M1-M3)
+* Speaker annotation requires a [HuggingFace Access Token](https://huggingface.co/docs/hub/security-tokens)
+
+<details>
+<summary><b>GPU Fix</b> for <i>Could not load library libcudnn_ops_infer.so.8.</i> (<b>click to expand</b>)</summary>
+<br>If you use <b>whisply</b> on a Linux system with a Nivida GPU and get this error:<br><br>
+
+```shell
+"Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory"
+```
+
+Run the following line in your CLI:
+
+```shell
+export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
+```
+
+Add this line to your Python environment to make it permanent:
+
+```shell
+echo "export LD_LIBRARY_PATH=\`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + \":\" + os.path.dirname(nvidia.cudnn.lib.__file__))'\`" >> path/to/your/python/env
+```
+
+For more information please refer to the <a href="https://github.com/SYSTRAN/faster-whisper" target="_blank">faster-whisper</a> GitHub page.
+
+</details>
+
+## Installation
+
+**1. Install `ffmpeg`**
+
+```markdown
+--- macOS ---
+brew install ffmpeg
+
+--- Linux ---
+sudo apt-get update
+sudo apt-get install ffmpeg
+
+--- Windows ----
+https://ffmpeg.org/download.html
+```
+
+**2. Clone this repository and change to project folder**
+
+```shell
+git clone https://github.com/tsmdt/whisply.git
+```
+
+```shell
+cd whisply
+```
+
+**3. Create a Python virtual environment**
+
+```python
+python3.11 -m venv venv
+```
+
+**4. Activate the Python virtual environment**
+
+```shell
+source venv/bin/activate
+```
+
+**5. Install `whisply` with `pip`**
+
+```python
+pip install .
+```
+
+## Usage
+
+```shell
+ Usage: whisply [OPTIONS]
+
+ WHISPLY 💬 Transcribe, translate, annotate and subtitle audio and video files with OpenAI's Whisper ... fast!
+
+╭─ Options ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+│ --files               -f       TEXT                Path to file, folder, URL or .list to process. [default: None]                                          │
+│ --output_dir          -o       DIRECTORY           Folder where transcripts should be saved. [default: transcriptions]                                     │
+│ --device              -d       [auto|cpu|gpu|mps]  Select the computation device: CPU, GPU (NVIDIA), or MPS (Mac M1-M3). [default: auto]                   │
+│ --model               -m       TEXT                Whisper model to use (List models via --list_models). [default: large-v2]                               │
+│ --lang                -l       TEXT                Language of provided file(s) ("en", "de") (Default: auto-detection). [default: None]                    │
+│ --annotate            -a                           Enable speaker annotation (Saves .rttm).                                                                │
+│ --hf_token            -hf      TEXT                HuggingFace Access token required for speaker annotation. [default: None]                               │
+│ --translate           -t                           Translate transcription to English.                                                                     │
+│ --subtitle            -s                           Create subtitles (Saves .srt, .vtt and .webvtt).                                                        │
+│ --sub_length                   INTEGER             Subtitle segment length in words [default: 5]                                                           │
+│ --verbose             -v                           Print text chunks during transcription.                                                                 │
+│ --config                       PATH                Path to configuration file. [default: None]                                                             │
+│ --list_filetypes                                   List supported audio and video file types.                                                              │
+│ --list_models                                      List available models.                                                                                  │
+│ --install-completion                               Install completion for the current shell.                                                               │
+│ --show-completion                                  Show completion for the current shell, to copy it or customize the installation.                        │
+│ --help                                             Show this message and exit.                                                                             │
+╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+  ```
+
+### Speaker annotation and diarization
+
+#### Requirements
+
+In order to annotate speakers using `--annotate` you need to provide a valid [HuggingFace](https://huggingface.co) access token using the `--hf_token` option. Additionally, you must accept the terms and conditions for both version 3.0 and version 3.1 of the `pyannote` segmentation model. For detailed instructions, refer to the *Requirements* section on the [pyannote model page on HuggingFace](https://huggingface.co/pyannote/speaker-diarization-3.1).
+
+#### How speaker annotation works
+
+`whisply` uses [whisperX](https://github.com/m-bain/whisperX) for speaker diarization and annotation. Instead of returning chunk-level timestamps like the standard `Whisper` implementation `whisperX` is able to return word-level timestamps as well as annotating speakers word by word, thus returning much more precise annotations.
+
+Out of the box `whisperX` will not provide timestamps for words containing only numbers (e.g. "1.5" or "2024"): `whisply` fixes those instances through timestamp approximation. Other known limitations of `whisperX` include:
+
+* inaccurate speaker diarization if multiple speakers talk at the same time
+* to provide word-level timestamps and annotations `whisperX` uses language specific alignment models; out of the box `whisperX` supports these languages: `en, fr, de, es, it, ja, zh, nl, uk, pt`.
+
+Refer to the [whisperX GitHub page](https://github.com/m-bain/whisperX) for more information.
+
+
+### Batch processing
+
+Instead of providing a file, folder or URL by using the `--files` option you can pass a `.list` with a mix of files, folders and URLs for processing. 
+
+Example:
+
+```shell
+$ cat my_files.list
+
+video_01.mp4
+video_02.mp4
+./my_files/
+https://youtu.be/KtOayYXEsN4?si=-0MS6KXbEWXA7dqo
+```
+
+#### Using config files for batch processing
+
+You can provide a `.json` config file by using the `--config` option which makes batch processing easy. An example config looks like this:
+
+```markdown
+{
+    "files": "./files/my_files.list",          # Path to your files
+    "output_dir": "./transcriptions",          # Output folder where transcriptions are saved
+    "device": "auto",                          # AUTO, GPU, MPS or CPU
+    "model": "large-v3-turbo",                 # Whisper model to use
+    "lang": null,                              # Null for auto-detection or language codes ("en", "de", ...)
+    "annotate": false,                         # Annotate speakers 
+    "hf_token": "HuggingFace Access Token",    # Your HuggingFace Access Token (needed for annotations)
+    "translate": false,                        # Translate to English
+    "subtitle": false,                         # Subtitle file(s)
+    "sub_length": 10,                          # Length of each subtitle block in number of words
+    "verbose": false                           # Print transcription segments while processing 
+}
+```

whisply-0.3/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"

whisply-0.3/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+