23 lines
392 B
Markdown
23 lines
392 B
Markdown
|
# 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
|
||
|
|
python stt_runner.py \
|
||
|
|
--conv-frontend=path/conv_frontend.onnx \
|
||
|
|
--encoder=path/encoder.onnx \
|
||
|
|
--decoder=path/decoder.onnx \
|
||
|
|
--tokenizer=path/tokenizer \
|
||
|
|
audio1.wav audio2.wav ...
|
||
|
|
```
|
||
|
|
|