Add multilingual STT support and config UI/runtime updates

This commit is contained in:
Thales Maciel 2026-02-27 12:38:13 -03:00
parent ed950cb7c4
commit 4a69c3d333
26 changed files with 2207 additions and 465 deletions

View file

@ -64,16 +64,18 @@ uv sync --extra x11
## Quickstart
```bash
uv run python3 src/aman.py run
uv run aman run
```
On first launch, Aman opens a graphical setup wizard automatically.
The wizard asks for:
On first launch, Aman opens a graphical settings window automatically.
It includes sections for:
- microphone input
- hotkey
- output backend
- writing profile
- runtime and model strategy
- help/about actions
## Config
@ -81,9 +83,30 @@ Create `~/.config/aman/config.json` (or let `aman` create it automatically on fi
```json
{
"config_version": 1,
"daemon": { "hotkey": "Cmd+m" },
"recording": { "input": "0" },
"stt": { "model": "base", "device": "cpu" },
"stt": {
"provider": "local_whisper",
"model": "base",
"device": "cpu",
"language": "auto"
},
"llm": { "provider": "local_llama" },
"models": {
"allow_custom_models": false,
"whisper_model_path": "",
"llm_model_path": ""
},
"external_api": {
"enabled": false,
"provider": "openai",
"base_url": "https://api.openai.com/v1",
"model": "gpt-4o-mini",
"timeout_ms": 15000,
"max_retries": 2,
"api_key_env_var": "AMAN_EXTERNAL_API_KEY"
},
"injection": {
"backend": "clipboard",
"remove_transcription_from_clipboard": false
@ -105,6 +128,9 @@ Create `~/.config/aman/config.json` (or let `aman` create it automatically on fi
}
```
`config_version` is required and currently must be `1`. Legacy unversioned
configs are migrated automatically on load.
Recording input can be a device index (preferred) or a substring of the device
name.
If `recording.input` is explicitly set and cannot be resolved, startup fails
@ -120,6 +146,12 @@ Profile options:
- `ux.profile=polished`: same cleanup depth as default.
- `advanced.strict_startup=true`: keep fail-fast startup validation behavior.
Transcription language:
- `stt.language=auto` (default) enables Whisper auto-detection.
- You can pin language with Whisper codes (for example `en`, `es`, `pt`, `ja`, `zh`) or common names like `English`/`Spanish`.
- If a pinned language hint is rejected by the runtime, Aman logs a warning and retries with auto-detect.
Hotkey notes:
- Use one key plus optional modifiers (for example `Cmd+m`, `Super+m`, `Ctrl+space`).
@ -131,6 +163,15 @@ Model downloads use a network timeout and SHA256 verification before activation.
Cached models are checksum-verified on startup; mismatches trigger a forced
redownload.
Provider policy:
- `Aman-managed` mode (recommended) is the canonical supported UX:
Aman handles model lifecycle and safe defaults for you.
- `Expert mode` is opt-in and exposes custom providers/models for advanced users.
- External API auth is environment-variable based (`external_api.api_key_env_var`);
no API key is stored in config.
- Custom local model paths are only active with `models.allow_custom_models=true`.
Use `-v/--verbose` to enable DEBUG logs, including recognized/processed
transcript text and llama.cpp logs (`llama::` prefix). Without `-v`, logs are
INFO level.
@ -150,9 +191,7 @@ STT hinting:
## systemd user service
```bash
mkdir -p ~/.local/share/aman/src/assets
cp src/*.py ~/.local/share/aman/src/
cp src/assets/*.png ~/.local/share/aman/src/assets/
uv pip install --user .
cp systemd/aman.service ~/.config/systemd/user/aman.service
systemctl --user daemon-reload
systemctl --user enable --now aman
@ -160,7 +199,7 @@ systemctl --user enable --now aman
Service notes:
- The user unit launches `uv` via `/usr/bin/env`; ensure `uv` is available in your user `PATH` (for example `~/.local/bin`).
- The user unit launches `aman` from `PATH`; ensure `~/.local/bin` is present in your user PATH.
- Inspect failures with `systemctl --user status aman` and `journalctl --user -u aman -f`.
## Usage
@ -171,8 +210,8 @@ Service notes:
- `Esc` is only captured during active recording.
- Recording start is aborted if the cancel listener cannot be armed.
- Transcript contents are logged only when `-v/--verbose` is used.
- Tray menu includes: `Setup Aman...`, `Pause/Resume Aman`, `Reload Config`, `Run Diagnostics`, `Open Config Path`, and `Quit`.
- If setup is not completed, Aman enters a `Setup Required` tray mode and does not capture audio.
- Tray menu includes: `Settings...`, `Help`, `About`, `Pause/Resume Aman`, `Reload Config`, `Run Diagnostics`, `Open Config Path`, and `Quit`.
- If required settings are not saved, Aman enters a `Settings Required` tray mode and does not capture audio.
Wayland note:
@ -186,20 +225,24 @@ Injection backends:
AI processing:
- Local llama.cpp model only (no remote provider configuration).
- Default local llama.cpp model.
- Optional external API provider through `llm.provider=external_api`.
Control:
```bash
make run
make doctor
make self-check
make check
```
CLI (internal/support fallback):
CLI (internal/support fallback, mostly for automation/tests):
```bash
uv run python3 src/aman.py run --config ~/.config/aman/config.json
uv run python3 src/aman.py doctor --config ~/.config/aman/config.json --json
uv run python3 src/aman.py init --config ~/.config/aman/config.json --force
uv run aman run --config ~/.config/aman/config.json
uv run aman doctor --config ~/.config/aman/config.json --json
uv run aman self-check --config ~/.config/aman/config.json --json
uv run aman version
uv run aman init --config ~/.config/aman/config.json --force
```