hueso/gajim-plugins
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README

Browse Source
This commit is contained in:
mesonium
2024-07-03 20:01:49 +02:00
committed by hueso
parent 24644f7fd4
commit 2dae45d2aa
2 changed files with 27 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
stt_voice_messages/README.md
View File

@@ -1,28 +1,33 @@
# Requirements # About
## STT Models This plugin allows you in conjuction with a _general-purpose speech recognition model_ to transcribe your voice messages to text.
### openai-whisper https://github.com/openai/whisper In order to make use of this plugin, you need to have at least one of the following models installed:
#### Installation #### OpenAI Whisper
`pip install -U openai-whisper` will install - Website: https://github.com/openai/whisper
- Installable by: `pip install -U openai-whisper`
``` #### Faster Whisper
mpmath, urllib3, tqdm, sympy, regex, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, - Website: https://github.com/SYSTRAN/faster-whisper
nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, - Installable by: `pip install -U faster_whisper`
nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, networkx,
MarkupSafe, llvmlite, fsspec, filelock, charset-normalizer, certifi, triton,
requests, nvidia-cusparse-cu12, nvidia-cudnn-cu12, numba, jinja2, tiktoken,
nvidia-cusolver-cu12, torch, openai-whisper
```
#### Models
| Multi Langual Model | Download Size | VRAM Requirement | Relative Speed | # Hint
|---------------------|---------------| ---------------- |----------------|
| Tiny | 70 MB | ~1 GB | ~32x | _**The plugin is very much POC at this stage!**_
| Base | 140 MB | ~1 GB | ~16x |
| Small | 460 MB | ~2 GB | ~6x | Currently a chosen model will be on first downloaded in the background, during which
| Medium | 1.4 GB | ~5 GB | ~2x | Gajim's UI may not respond.
| Large | 2.9 GB | ~10 GB | ~1x |
Typical model sizes are in case of OpenAI Whisper:
| Multi Langual Model | Download Size |
|---------------------|---------------|
| Tiny | 70 MB |
| Base | 140 MB |
| Small | 460 MB |
| Medium | 1.4 GB |
| Large | 2.9 GB |

2
stt_voice_messages/gtk/config_dialog.py
View File

@@ -207,7 +207,7 @@ class STTVoiceMessagesConfigDialog(Gtk.ApplicationWindow):
self.config = config self.config = config
self.plugin = self.config.plugin self.plugin = self.config.plugin
self._add_prefs(prefs) self._add_prefs(prefs)
self.show_all() self.show_all()
def _add_prefs(self, prefs: list[tuple[str, type[PreferenceBox]]]): def _add_prefs(self, prefs: list[tuple[str, type[PreferenceBox]]]):