# Nendo Plugin Transcribe Whisper
<br>
<p align="left">
<img src="https://okio.ai/docs/assets/nendo_core_logo.png" width="350" alt="nendo core">
</p>
<br>
<p align="left">
<a href="https://okio.ai" target="_blank">
<img src="https://img.shields.io/website/https/okio.ai" alt="Website">
</a>
<a href="https://twitter.com/okio_ai" target="_blank">
<img src="https://img.shields.io/twitter/url/https/twitter.com/okio_ai.svg?style=social&label=Follow%20%40okio_ai" alt="Twitter">
</a>
<a href="https://discord.gg/gaZMZKzScj" target="_blank">
<img src="https://dcbadge.vercel.app/api/server/XpkUsjwXTp?compact=true&style=flat" alt="Discord">
</a>
</p>
---
A nendo plugin for speech transcription, based on Whisper by OpenAI.
## Features
- Fast speech transcription with optional word-level timestamps.
## Requirements
Since we depend on `transformers`, please make sure that you fulfill their requirements.
You also need Pytorch installed on your system, please refer to the [pytorch installation instructions](https://pytorch.org/get-started/locally/).
## Installation
1. [Install Nendo](https://github.com/okio-ai/nendo#installation)
2. `pip install nendo-plugin-transcribe-whisper`
If you have a cuda GPU on your machine you can also install `flash-attn` to get an additional speedup:
`pip install flash-attn --no-build-isolation`
Then set `ATTN_IMPLEMENTATION=flash_attention_2` in your environment variables.
## Usage
```pycon
>>> from nendo import Nendo
>>> nd = Nendo(plugins=["nendo_plugin_transcribe_whisper"])
>>> track = nd.library.add_track(file_path="path/to/file.mp3")
>>> nd.plugins.transcribe_whisper(track=track)
>>> track.get_plugin_value("transcription")
```
## Contributing
Visit our docs to learn all about how to contribute to Nendo: [Contributing](https://okio.ai/docs/contributing/)
## License
Nendo: MIT License
Pretrained models: The weights are released under the Apache 2.0 license.
Raw data
{
"_id": null,
"home_page": "https://okio.ai",
"name": "nendo-plugin-transcribe-whisper",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8,<3.11",
"maintainer_email": "",
"keywords": "AI,generative,music,okio,nendo,audio production,audio transcription,music analysis,song analysis",
"author": "Aaron Abebe",
"author_email": "aaron@okio.ai",
"download_url": "https://files.pythonhosted.org/packages/a4/f1/d3401aedb19b1a2650d10872524f885129a6114ce6dc4a72bea373613256/nendo_plugin_transcribe_whisper-0.1.0.tar.gz",
"platform": null,
"description": "# Nendo Plugin Transcribe Whisper\n\n<br>\n<p align=\"left\">\n <img src=\"https://okio.ai/docs/assets/nendo_core_logo.png\" width=\"350\" alt=\"nendo core\">\n</p>\n<br>\n\n<p align=\"left\">\n<a href=\"https://okio.ai\" target=\"_blank\">\n <img src=\"https://img.shields.io/website/https/okio.ai\" alt=\"Website\">\n</a>\n<a href=\"https://twitter.com/okio_ai\" target=\"_blank\">\n <img src=\"https://img.shields.io/twitter/url/https/twitter.com/okio_ai.svg?style=social&label=Follow%20%40okio_ai\" alt=\"Twitter\">\n</a>\n<a href=\"https://discord.gg/gaZMZKzScj\" target=\"_blank\">\n <img src=\"https://dcbadge.vercel.app/api/server/XpkUsjwXTp?compact=true&style=flat\" alt=\"Discord\">\n</a>\n</p>\n\n---\n\nA nendo plugin for speech transcription, based on Whisper by OpenAI.\n\n## Features\n\n- Fast speech transcription with optional word-level timestamps.\n\n## Requirements\n\nSince we depend on `transformers`, please make sure that you fulfill their requirements.\nYou also need Pytorch installed on your system, please refer to the [pytorch installation instructions](https://pytorch.org/get-started/locally/).\n\n## Installation\n\n1. [Install Nendo](https://github.com/okio-ai/nendo#installation)\n2. `pip install nendo-plugin-transcribe-whisper`\n\nIf you have a cuda GPU on your machine you can also install `flash-attn` to get an additional speedup:\n\n`pip install flash-attn --no-build-isolation`\n\nThen set `ATTN_IMPLEMENTATION=flash_attention_2` in your environment variables.\n\n## Usage\n```pycon\n>>> from nendo import Nendo\n>>> nd = Nendo(plugins=[\"nendo_plugin_transcribe_whisper\"])\n>>> track = nd.library.add_track(file_path=\"path/to/file.mp3\")\n\n>>> nd.plugins.transcribe_whisper(track=track)\n>>> track.get_plugin_value(\"transcription\")\n```\n\n## Contributing\nVisit our docs to learn all about how to contribute to Nendo: [Contributing](https://okio.ai/docs/contributing/)\n\n## License\nNendo: MIT License\n\nPretrained models: The weights are released under the Apache 2.0 license.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A nendo plugin for speech transcription, based on Whisper by OpenAI.",
"version": "0.1.0",
"project_urls": {
"Homepage": "https://okio.ai",
"Repository": "https://github.com/okio-ai/nendo_plugin_transcribe_whisper"
},
"split_keywords": [
"ai",
"generative",
"music",
"okio",
"nendo",
"audio production",
"audio transcription",
"music analysis",
"song analysis"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "608e1ed3c433c9733ae6ada8d9b7b8e39c1a5a8b074f98feb1666ed933b84b58",
"md5": "13cd9bf2a13ae4c0e2ebd61aff5b848c",
"sha256": "b90d094e63f345a7fc6cdefc6fd8e430921690e899f3a45a4d1fbc5016be0131"
},
"downloads": -1,
"filename": "nendo_plugin_transcribe_whisper-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "13cd9bf2a13ae4c0e2ebd61aff5b848c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8,<3.11",
"size": 5461,
"upload_time": "2024-02-21T10:26:14",
"upload_time_iso_8601": "2024-02-21T10:26:14.429944Z",
"url": "https://files.pythonhosted.org/packages/60/8e/1ed3c433c9733ae6ada8d9b7b8e39c1a5a8b074f98feb1666ed933b84b58/nendo_plugin_transcribe_whisper-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "a4f1d3401aedb19b1a2650d10872524f885129a6114ce6dc4a72bea373613256",
"md5": "405cc9921f5acb93872a41749734538a",
"sha256": "e9c5326476588e41495c41838a1f975b88973733f16d9b68d3f3c81a74c92b78"
},
"downloads": -1,
"filename": "nendo_plugin_transcribe_whisper-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "405cc9921f5acb93872a41749734538a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8,<3.11",
"size": 5244,
"upload_time": "2024-02-21T10:26:16",
"upload_time_iso_8601": "2024-02-21T10:26:16.289426Z",
"url": "https://files.pythonhosted.org/packages/a4/f1/d3401aedb19b1a2650d10872524f885129a6114ce6dc4a72bea373613256/nendo_plugin_transcribe_whisper-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-21 10:26:16",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "okio-ai",
"github_project": "nendo_plugin_transcribe_whisper",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "nendo-plugin-transcribe-whisper"
}
JSON
