2026-09-15 13:50:17 +07:00
|
|
|
# STT Runner
|
|
|
|
|
|
|
|
|
|
Speech-to-Text transcription using sherpa-onnx + Qwen3-ASR.
|
|
|
|
|
|
|
|
|
|
## Installation
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
python3 -m venv .venv
|
|
|
|
|
.venv/bin/pip install -r requirements.txt
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
## Usage
|
|
|
|
|
|
|
|
|
|
```bash
|
2026-09-15 14:59:25 +07:00
|
|
|
python stt_runner.py [--language=Indonesian] audio1.wav audio2.wav ...
|
2026-09-15 13:50:17 +07:00
|
|
|
```
|
|
|
|
|
|
2026-09-15 14:59:25 +07:00
|
|
|
## Configuration
|
|
|
|
|
|
|
|
|
|
Model paths and inference parameters are hardcoded in `config/`:
|
|
|
|
|
|
|
|
|
|
- `config/model.py` — model paths (conv_frontend, encoder, decoder, tokenizer under `models/`)
|
|
|
|
|
- `config/asr.py` — inference params: `LANGUAGE`, `HOTWORDS`, `NUM_THREADS`, `PROVIDER`, `SAMPLE_RATE`, `FEATURE_DIM`, `MAX_TOTAL_LEN`, `MAX_NEW_TOKENS`
|
|
|
|
|
|
|
|
|
|
`LANGUAGE` defaults to `""` (all languages / auto-detect). Passing `--language` on the CLI overrides it.
|
|
|
|
|
|
|
|
|
|
## Download Model (Qwen3-ASR 1.7B int8)
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
BASE="https://modelscope.cn/models/zengshuishui/Qwen3-ASR-onnx/resolve/master"
|
|
|
|
|
mkdir -p models/model_1.7B models/tokenizer
|
|
|
|
|
wget -O models/model_1.7B/conv_frontend.onnx "$BASE/model_1.7B/conv_frontend.onnx"
|
|
|
|
|
wget -O models/model_1.7B/encoder.int8.onnx "$BASE/model_1.7B/encoder.int8.onnx"
|
|
|
|
|
wget -O models/model_1.7B/decoder.int8.onnx "$BASE/model_1.7B/decoder.int8.onnx"
|
|
|
|
|
for f in vocab.json merges.txt tokenizer_config.json preprocessor_config.json config.json chat_template.json; do
|
|
|
|
|
wget -O "models/tokenizer/$f" "$BASE/tokenizer/$f"
|
|
|
|
|
done
|
|
|
|
|
```
|
