| | |
|---|
| | | ## Using paraformer with libtorch |
|---|
| | | ## Using funasr with libtorch |
|---|
| | | |
|---|
| | | [FunASR](https://github.com/alibaba-damo-academy/FunASR) hopes to build a bridge between academic research and industrial applications on speech recognition. By supporting the training & finetuning of the industrial-grade speech recognition model released on ModelScope, researchers and developers can conduct research and production of speech recognition models more conveniently, and promote the development of speech recognition ecology. ASR for Fun！ |
|---|
| | | |
|---|
| | | ### Introduction |
|---|
| | | - Model comes from [speech_paraformer](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary). |
|---|
| | |
|---|
| | | 1. Export the model. |
|---|
| | | - Command: (`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. |
|---|
| | | |
|---|
| | | `export_dir`: the dir where the onnx is export. |
|---|
| | | |
|---|
| | | More details ref to ([export docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)) |
|---|
| | | |
|---|
| | | - `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 --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type torch --quantize 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 --model-name ./damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type torch --quantize 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 |
|---|
| | | ``` |
|---|
| | | 2. Install the `funasr_torch`. |
|---|
| | | ```shell |
|---|
| | | pip install funasr_torch -i https://pypi.Python.org/simple |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | |
|---|
| | | 3. Run the demo. |
|---|
| | | - Model_dir: the model path, which contains `model.torchscripts`, `config.yaml`, `am.mvn`. |
|---|
| | |
|---|
| | | - Output: `List[str]`: recognition result. |
|---|
| | | - Example: |
|---|
| | | ```python |
|---|
| | | from torch_paraformer import Paraformer |
|---|
| | | from funasr_torch 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) |
|---|
| | |
|---|
| | | |
|---|
| | | 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 | |
|---|
| | | | Backend | RTF (FP32) | |
|---|
| | | |:--------:|:----------:| |
|---|
| | | | Pytorch | 0.110 | |
|---|
| | | | Libtorch | 0.048 | |
|---|
| | | | Onnx | 0.038 | |
|---|
| | | |
|---|
| | | ## Acknowledge |
|---|
| | | This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR). |
|---|
