| Name | DrDictaphone JSON |
| Version |
0.9.6
JSON |
| download |
| home_page | None |
| Summary | Dictation app for the terminal and Neovim |
| upload_time | 2024-09-08 13:13:03 |
| maintainer | None |
| docs_url | None |
| author | Ole Kliemann |
| requires_python | >=3.10 |
| license | LICENSE |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# DrDictaphone
Dictation app for the terminal and Neovim, using Whisper for transcription and ChatGPT for post-processing.
### Installation
You can use the installation script:
```
curl https://raw.githubusercontent.com/olekli/DrDictaphone/main/script/install.sh | sh
```
Or create a virtual environment and do:
```
pip install drdictaphone
python -m drdictaphone.cli install ~/DrDictaphone
```
Place OpenAI API key in `~/DrDictaphone/config/openai_api_key`.
### Running
To start the standalone app, do `./drdictaphone`.
To start only the server, do `./drdictaphone server`.
Shutdown a running server by doing `./drdictaphone shutdown`.
### Neovim Plugin
If you are not already using Python plugins in Neovim,
you need to create a virtual environment for Neovim to use.
Tell Neovim about it by adding to your `init.vim`:
```
let g:python3_host_prog = '~/.neovim-venv/bin/python'
```
(Or wherever your venv is located.)
Inside this virtual environment, install the Neovim plugin:
```
pip install drdictaphone-neovim-plugin
```
Now you need to add the plugin to your Neovim config directory:
```
ln -s ~/.neovim-venv/lib/python3.11/site-packages/drdictaphone_neovim/DrDictaphone.py ~/.config/nvim/rplugin/python3/.
```
(Your paths may vary.)
Then start the server. Do `:UpdateRemotePlugins` once in Neovim, restart. Use `DrDictaphoneSetProfile`, `DrDictaphoneToggle` vim commands.
### Controlling Standalone App:
- `s`: select profile
- `p`: start / stop and transcribe recording
- `d`: stop and discard recording
- `q`: exit
### Profiles
Profiles consist of:
- `topic` for transcribing and post-processing, a list of strings
- `language` to use for the transcriber, a string
- `output` directory, a string
- `output_command` to pipe output to
- `enable_vad` whether or not to enable VAD, a bool, defaults to `false`
Output will be written to a timestamped file in the output directory.
VAD will filter recordings for parts with voice before processing them.
### Post-Processor
The Post-Processor specs consist of:
- `instructions` for the post-processor, either a filename to load from or a list of strings
- `gpt_model` to use for post-processing, either a filename to load from or an object
- `options` to use for post-processing, either a filename to load from or an object
- `tools` to use for the post-processor, either a filename to load from or an object
The context for the post-processor is built from the profile and the post-processor specs. Settings in the profile take precedence over settings in the specs.
Raw data
{
"_id": null,
"home_page": null,
"name": "DrDictaphone",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Ole Kliemann",
"author_email": "mail@olekliemann.de",
"download_url": "https://files.pythonhosted.org/packages/47/78/35f2729049346bf1fc8d293bc6171b1955a67fd8c6acfd7052f6a6bf76fc/drdictaphone-0.9.6.tar.gz",
"platform": null,
"description": "# DrDictaphone\n\nDictation app for the terminal and Neovim, using Whisper for transcription and ChatGPT for post-processing.\n\n### Installation\n\nYou can use the installation script:\n```\ncurl https://raw.githubusercontent.com/olekli/DrDictaphone/main/script/install.sh | sh\n```\n\nOr create a virtual environment and do:\n```\npip install drdictaphone\npython -m drdictaphone.cli install ~/DrDictaphone\n```\n\nPlace OpenAI API key in `~/DrDictaphone/config/openai_api_key`.\n\n### Running\n\nTo start the standalone app, do `./drdictaphone`.\n\nTo start only the server, do `./drdictaphone server`.\n\nShutdown a running server by doing `./drdictaphone shutdown`.\n\n### Neovim Plugin\n\nIf you are not already using Python plugins in Neovim,\nyou need to create a virtual environment for Neovim to use.\nTell Neovim about it by adding to your `init.vim`:\n```\nlet g:python3_host_prog = '~/.neovim-venv/bin/python'\n```\n(Or wherever your venv is located.)\n\nInside this virtual environment, install the Neovim plugin:\n```\npip install drdictaphone-neovim-plugin\n```\n\nNow you need to add the plugin to your Neovim config directory:\n```\nln -s ~/.neovim-venv/lib/python3.11/site-packages/drdictaphone_neovim/DrDictaphone.py ~/.config/nvim/rplugin/python3/.\n```\n(Your paths may vary.)\n\nThen start the server. Do `:UpdateRemotePlugins` once in Neovim, restart. Use `DrDictaphoneSetProfile`, `DrDictaphoneToggle` vim commands.\n\n### Controlling Standalone App:\n\n- `s`: select profile\n- `p`: start / stop and transcribe recording\n- `d`: stop and discard recording\n- `q`: exit\n\n### Profiles\n\nProfiles consist of:\n\n- `topic` for transcribing and post-processing, a list of strings\n- `language` to use for the transcriber, a string\n- `output` directory, a string\n- `output_command` to pipe output to\n- `enable_vad` whether or not to enable VAD, a bool, defaults to `false`\n\nOutput will be written to a timestamped file in the output directory.\n\nVAD will filter recordings for parts with voice before processing them.\n\n### Post-Processor\n\nThe Post-Processor specs consist of:\n\n- `instructions` for the post-processor, either a filename to load from or a list of strings\n- `gpt_model` to use for post-processing, either a filename to load from or an object\n- `options` to use for post-processing, either a filename to load from or an object\n- `tools` to use for the post-processor, either a filename to load from or an object\n\nThe context for the post-processor is built from the profile and the post-processor specs. Settings in the profile take precedence over settings in the specs.\n",
"bugtrack_url": null,
"license": "LICENSE",
"summary": "Dictation app for the terminal and Neovim",
"version": "0.9.6",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "c6432816fafd93e46605254af01ec0e06335de58f6a4e724de6734601d94271a",
"md5": "6e7de1af77564e9dabb80a90244d19bc",
"sha256": "0bcf65b6cbfd68b782e7e48d99f290cb3cfc3bca16080d0e1846d40c44f9c8d6"
},
"downloads": -1,
"filename": "drdictaphone-0.9.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6e7de1af77564e9dabb80a90244d19bc",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 36468,
"upload_time": "2024-09-08T13:13:01",
"upload_time_iso_8601": "2024-09-08T13:13:01.057748Z",
"url": "https://files.pythonhosted.org/packages/c6/43/2816fafd93e46605254af01ec0e06335de58f6a4e724de6734601d94271a/drdictaphone-0.9.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "477835f2729049346bf1fc8d293bc6171b1955a67fd8c6acfd7052f6a6bf76fc",
"md5": "380992ea45ed36288ef533998ce6fb49",
"sha256": "1f05fd1ccd9f21c89139054c10135d664905b276456e51b459eebca176484bef"
},
"downloads": -1,
"filename": "drdictaphone-0.9.6.tar.gz",
"has_sig": false,
"md5_digest": "380992ea45ed36288ef533998ce6fb49",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 21187,
"upload_time": "2024-09-08T13:13:03",
"upload_time_iso_8601": "2024-09-08T13:13:03.255804Z",
"url": "https://files.pythonhosted.org/packages/47/78/35f2729049346bf1fc8d293bc6171b1955a67fd8c6acfd7052f6a6bf76fc/drdictaphone-0.9.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-08 13:13:03",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "drdictaphone"
}
