speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

torchscripts

Browse Source
This commit is contained in:
游雁 2023-03-02 20:23:39 +08:00
parent 548153260b
commit ec3ccbea9f
1 changed files with 8 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
funasr/runtime/python/libtorch/README.md
View File

@ -19,25 +19,21 @@
- `e.g.`, Export model from modelscope
```shell
python -m funasr.export.export_model 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" true
python -m funasr.export.export_model 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" false
```
- `e.g.`, Export model from local path, the model'name must be `model.pb`.
```shell
python -m funasr.export.export_model '/mnt/workspace/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" true
python -m funasr.export.export_model '/mnt/workspace/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" false
```
2. Install the `torch_paraformer`.
- Build the torch_paraformer `whl`
```shell
git clone https://github.com/alibaba/FunASR.git && cd FunASR
cd funasr/runtime/python/libtorch
python setup.py bdist_wheel
```
- Install the build `whl`
```bash
pip install dist/torch_paraformer-0.0.1-py3-none-any.whl
```
```shell
git clone https://github.com/alibaba/FunASR.git && cd FunASR
cd funasr/runtime/python/libtorch
python setup.py install
```
3. Run the demo.
- Model_dir: the model path, which contains `model.torchscripts`, `config.yaml`, `am.mvn`.