| | |
|---|
| | | ## Using paraformer with ONNXRuntime |
|---|
| | | # ONNXRuntime-python |
|---|
| | | |
|---|
| | | <p align="left"> |
|---|
| | | <a href=""><img src="https://img.shields.io/badge/Python->=3.7,<=3.10-aff.svg"></a> |
|---|
| | | <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-pink.svg"></a> |
|---|
| | | </p> |
|---|
| | | ## Export the model |
|---|
| | | ### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation) |
|---|
| | | |
|---|
| | | ### Introduction |
|---|
| | | - Model comes from [speech_paraformer](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary). |
|---|
| | | ```shell |
|---|
| | | pip3 install torch torchaudio |
|---|
| | | pip install -U modelscope |
|---|
| | | pip install -U funasr |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | ### Export [onnx model](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export) |
|---|
| | | |
|---|
| | | ```shell |
|---|
| | | python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | |
|---|
| | | ### Steps: |
|---|
| | | 1. Download the whole directory |
|---|
| | | ## Install the `funasr_onnx` |
|---|
| | | |
|---|
| | | install from pip |
|---|
| | | ```shell |
|---|
| | | pip install -U funasr_onnx |
|---|
| | | # For the users in China, you could install with the command: |
|---|
| | | # pip install -U funasr_onnx -i https://mirror.sjtu.edu.cn/pypi/web/simple |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | or install from source code |
|---|
| | | |
|---|
| | | ```shell |
|---|
| | | git clone https://github.com/alibaba/FunASR.git && cd FunASR |
|---|
| | | cd funasr/runtime/python/onnxruntime/paraformer/rapid_paraformer |
|---|
| | | cd funasr/runtime/python/onnxruntime |
|---|
| | | pip install -e ./ |
|---|
| | | # For the users in China, you could install with the command: |
|---|
| | | # pip install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple |
|---|
| | | ``` |
|---|
| | | 2. Install the related packages. |
|---|
| | | ```bash |
|---|
| | | pip install -r requirements.txt |
|---|
| | | ``` |
|---|
| | | 3. Export the model. |
|---|
| | | |
|---|
| | | `Tips`: torch 1.11.0 is required. |
|---|
| | | |
|---|
| | | ```shell |
|---|
| | | python -m funasr.export.export_model [model_name] [export_dir] [true] |
|---|
| | | ``` |
|---|
| | | `model_name`: the model is to export. |
|---|
| | | ## Run the demo |
|---|
| | | - Model_dir: the model path, which contains `model.onnx`, `config.yaml`, `am.mvn`. |
|---|
| | | - Input: wav formt file, support formats: `str, np.ndarray, List[str]` |
|---|
| | | - Output: `List[str]`: recognition result. |
|---|
| | | - Example: |
|---|
| | | ```python |
|---|
| | | from funasr_onnx import Paraformer |
|---|
| | | |
|---|
| | | `export_dir`: the dir where the onnx is export. |
|---|
| | | model_dir = "/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" |
|---|
| | | model = Paraformer(model_dir, batch_size=1) |
|---|
| | | |
|---|
| | | More details ref to ([export docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)) |
|---|
| | | wav_path = ['/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav'] |
|---|
| | | |
|---|
| | | result = model(wav_path) |
|---|
| | | print(result) |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | - `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 |
|---|
| | | ``` |
|---|
| | | - `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 |
|---|
| | | ``` |
|---|
| | | ## Performance benchmark |
|---|
| | | |
|---|
| | | 5. Run the demo. |
|---|
| | | - Model_dir: the model path, which contains `model.onnx`, `config.yaml`, `am.mvn`. |
|---|
| | | - Input: wav formt file, support formats: `str, np.ndarray, List[str]` |
|---|
| | | - Output: `List[str]`: recognition result. |
|---|
| | | - Example: |
|---|
| | | ```python |
|---|
| | | from paraformer_onnx import Paraformer |
|---|
| | | |
|---|
| | | model_dir = "/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" |
|---|
| | | model = Paraformer(model_dir, batch_size=1) |
|---|
| | | |
|---|
| | | wav_path = ['/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav'] |
|---|
| | | |
|---|
| | | result = model(wav_path) |
|---|
| | | print(result) |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | ## Speed |
|---|
| | | |
|---|
| | | Environment：Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz |
|---|
| | | |
|---|
| | | Test [wav, 5.53s, 100 times avg.](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav) |
|---|
| | | |
|---|
| | | | Backend | RTF | |
|---|
| | | |:-------:|:-----------------:| |
|---|
| | | | Pytorch | 0.110 | |
|---|
| | | | Onnx | 0.038 | |
|---|
| | | |
|---|
| | | Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_onnx.md) |
|---|
| | | |
|---|
| | | ## Acknowledge |
|---|
| | | 1. We acknowledge [SWHL](https://github.com/RapidAI/RapidASR) for contributing the onnxruntime(python api). |
|---|
| | | 1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR). |
|---|
| | | 2. We acknowledge [SWHL](https://github.com/RapidAI/RapidASR) for contributing the onnxruntime (for paraformer model). |
|---|
