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

fix benchmark links (#1092)

Browse Source
This commit is contained in:
Meng Wei 2023-11-15 16:24:51 +08:00 committed by GitHub
parent 0612ae780c
commit 12d694f94c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
runtime/python/libtorch/README.md
View File

@ -1,6 +1,7 @@
# Libtorch-python
## Export the model
### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation)
```shell
@ -18,14 +19,16 @@ pip install onnx onnxruntime # Optional, for onnx quantization
python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type torch --quantize True
```
## Install the `funasr_torch`.
## Install the `funasr_torch`
install from pip
```shell
pip install -U funasr_torch
# For the users in China, you could install with the command:
# pip install -U funasr_torch -i https://mirror.sjtu.edu.cn/pypi/web/simple
```
or install from source code
```shell
@ -36,11 +39,13 @@ pip install -e ./
# pip install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple
```
## Run the demo.
## Run the demo
- Model_dir: the model path, which contains `model.torchscripts`, `config.yaml`, `am.mvn`.
- Input: wav formt file, support formats: `str, np.ndarray, List[str]`
- Output: `List[str]`: recognition result.
- Example:
```python
from funasr_torch import Paraformer
@ -55,7 +60,7 @@ pip install -e ./
## Performance benchmark
Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_libtorch.md)
Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/benchmark_libtorch.md)
## Speed
@ -70,4 +75,5 @@ Test [wav, 5.53s, 100 times avg.](https://isv-data.oss-cn-hangzhou.aliyuncs.com/
| Onnx | 0.038 |
## Acknowledge
This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).

2
runtime/python/onnxruntime/README.md
View File

@ -180,7 +180,7 @@ Output: `List[str]`: recognition result
## Performance benchmark
Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/docs/benchmark_onnx.md)
Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/benchmark_onnx.md)
## Acknowledge