efforting.tech/stt-server
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

WebSocket server, language/task args, verbose flag, misc improvements #2

Merged
mikael-lovqvist merged 13 commits from mikael-lovqvists-claude-agent/stt-server:websocket-server into main 2026-06-07 09:27:02 +00:00
Conversation 0 Commits 13 Files Changed 7 +22 -2
2 changed files with 22 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit bdb1aac885 - Show all commits

19
README.md
View File

@@ -42,4 +42,21 @@ Pass `--compute-type <type>` to control the numeric precision used during infere
| `float16` | Slightly better accuracy, higher VRAM usage. |
| `int8` | CPU-friendly, lower quality. |
If you see a CUDA error about mismatched library versions at startup, use `setup-venv-local-build.sh` to build ctranslate2 against your system CUDA version rather than using the PyPI wheel.
If you see a CUDA error about mismatched library versions at startup, use `setup-venv-local-build.sh` to build ctranslate2 against your system CUDA version rather than using the PyPI wheel.
## Language and translation
By default the server auto-detects the spoken language and transcribes it as-is.
| Argument | Default | Notes |
|----------|---------|-------|
| `--language <code>` | none (auto-detect) | Force a specific language, e.g. `--language en` or `--language sv`. Speeds up detection and avoids misidentification. |
| `--task transcribe` | default | Output text in the spoken language. |
| `--task translate` | | Translate speech to English regardless of source language. |
> [!NOTE]
> The `.en` model variants (`base.en`, `small.en` etc.) are English-only and do not support `--task translate` or non-English `--language`. Use a multilingual model (`large-v3`, `medium`) for multilingual or translation use cases.
> [!WARNING]
> Omitting `--language` with a multilingual model and English-only speech may cause occasional misdetection. Pass `--language en` to avoid this if you only speak English.

5
stt-server.py
View File

@@ -120,6 +120,8 @@ parser = argparse.ArgumentParser()
parser.add_argument('--model', default='base.en')
parser.add_argument('--device', default='cuda')
parser.add_argument('--compute-type', default='int8_float16')
parser.add_argument('--language', default=None, help='language code (e.g. en, sv) or None for auto-detect')
parser.add_argument('--task', default='transcribe', choices=['transcribe', 'translate'], help='transcribe keeps the source language; translate converts to English')
parser.add_argument('--verbose', '-v', action='store_true')
args = parser.parse_args()
verbose = args.verbose
@@ -195,7 +197,8 @@ def transcription_worker():
try:
segments, _ = model.transcribe(
samples,
language='en',
language=args.language,
task=args.task,
word_timestamps=True,
vad_filter=False,
)