Add Parakeet v3 local STT model for multilingual dictation

v2 is English-only; v3 covers 25 European languages with automatic
language detection. The archive shares v2's filenames, architecture,
sample rate, and feature dim, so no runtime loader changes are needed.

Document that the `language` config field and PASEO_*_LANGUAGE vars
only steer the OpenAI STT provider — the local Parakeet models ignore
them, so multilingual local dictation means selecting the v3 model.
This commit is contained in:
Mohamed Boudra
2026-05-29 14:06:18 +07:00
parent d1eb976653
commit 524aef5d75
2 changed files with 35 additions and 4 deletions

View File

@@ -24,10 +24,19 @@ This keeps credentials and execution in your environment and avoids introducing
## Local Speech
Local speech defaults to model IDs `parakeet-tdt-0.6b-v2-int8` (STT) and `kokoro-en-v0_19` (TTS, speaker 0 / voice 00). STT language defaults to `en`.
Local speech defaults to model IDs `parakeet-tdt-0.6b-v2-int8` (STT) and `kokoro-en-v0_19` (TTS, speaker 0 / voice 00).
Missing models are downloaded at daemon startup into `$PASEO_HOME/models/local-speech`. Downloads happen only for missing files.
### Local STT models and language support
| Model ID | Languages |
| --------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `parakeet-tdt-0.6b-v2-int8` | English only (default). Includes punctuation and capitalization. |
| `parakeet-tdt-0.6b-v3-int8` | 25 European languages, auto-detected: Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Ukrainian. |
**To use a non-English language, switch the local STT model to `parakeet-tdt-0.6b-v3-int8`.** v3 detects the spoken language automatically — there is no per-language setting for it. The `language` field below does **not** steer the local Parakeet model (v2 is English-only, v3 auto-detects); it only applies to the OpenAI STT provider.
```json
{
"version": 1,
@@ -49,7 +58,20 @@ Missing models are downloaded at daemon startup into `$PASEO_HOME/models/local-s
}
```
Set `features.dictation.stt.language` for dictation and `features.voiceMode.stt.language` for realtime voice. If voice language is omitted, Paseo uses the dictation language before falling back to `en`.
For multilingual local dictation, set the model to v3 — it auto-detects the language, so no `language` field is needed:
```json
{
"version": 1,
"features": {
"dictation": {
"stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" }
}
}
}
```
The `language` field applies only to the OpenAI STT provider: set `features.dictation.stt.language` for dictation and `features.voiceMode.stt.language` for realtime voice. If voice language is omitted, Paseo uses the dictation language before falling back to `en`. It has no effect on the local Parakeet models.
## OpenAI Speech Option
@@ -78,8 +100,8 @@ You can switch dictation, voice STT, and voice TTS to OpenAI by setting provider
- `PASEO_LOCAL_MODELS_DIR`, local model storage directory
- `PASEO_DICTATION_LOCAL_STT_MODEL`, local dictation STT model ID
- `PASEO_VOICE_LOCAL_STT_MODEL`, `PASEO_VOICE_LOCAL_TTS_MODEL`, local voice STT/TTS model IDs
- `PASEO_DICTATION_LANGUAGE`, dictation STT language
- `PASEO_VOICE_LANGUAGE`, realtime voice STT language; falls back to `PASEO_DICTATION_LANGUAGE` when unset
- `PASEO_DICTATION_LANGUAGE`, dictation STT language (OpenAI STT only; ignored by local Parakeet)
- `PASEO_VOICE_LANGUAGE`, realtime voice STT language; falls back to `PASEO_DICTATION_LANGUAGE` when unset (OpenAI STT only; ignored by local Parakeet)
- `PASEO_VOICE_LOCAL_TTS_SPEAKER_ID`, `PASEO_VOICE_LOCAL_TTS_SPEED`, optional local voice TTS tuning
## Operational Notes