From 4ace5a95b052d338947fc88809a440ccd55cf6b4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 十一月 2023 16:39:52 +0800
Subject: [PATCH] funasr pages
---
funasr/export/README.md | 93 +++++++++++++++++++++++++++++++++++-----------
1 files changed, 71 insertions(+), 22 deletions(-)
diff --git a/funasr/export/README.md b/funasr/export/README.md
index 87ec240..bbb8bf8 100644
--- a/funasr/export/README.md
+++ b/funasr/export/README.md
@@ -1,44 +1,93 @@
+# Export models
## Environments
- funasr 0.1.7
- python 3.7
- torch 1.11.0
- modelscope 1.2.0
+### Install modelscope and funasr
-## Install modelscope and funasr
+The installation is the same as [funasr](https://github.com/alibaba-damo-academy/FunASR/blob/main/README.md#installation)
+```shell
+# pip3 install torch torchaudio
+pip install -U modelscope funasr
+# For the users in China, you could install with the command:
+# pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
+```
+### Install the quantization tools
+```shell
+pip install torch-quant # Optional, for torchscript quantization
+pip install onnx onnxruntime # Optional, for onnx quantization
+```
-The installation is the same as [funasr](../../README.md)
-
-## Export model
- `Tips`: torch1.11.0 is required.
+## Usage
+ `Tips`: torch>=1.11.0
```shell
- python -m funasr.export.export_model [model_name] [export_dir] [true/flase]
+ python -m funasr.export.export_model \
+ --model-name [model_name] \
+ --export-dir [export_dir] \
+ --type [onnx, torch] \
+ --quantize [true, false] \
+ --fallback-num [fallback_num]
```
- `model_name`: the model is to export.
+ `model-name`: the model is to export. It could be the models from modelscope, or local finetuned model(named: model.pb).
- `export_dir`: the dir where the onnx is export.
- `true`: export onnx format model, `false`: export torchscripts format model.
+ `export-dir`: the dir where the onnx is export.
-## For example
+ `type`: `onnx` or `torch`, export onnx format model or torchscript format model.
+
+ `quantize`: `true`, export quantized model at the same time; `false`, export fp32 model only.
+
+ `fallback-num`: specify the number of fallback layers to perform automatic mixed precision quantization.
+
+
### Export onnx format model
-Export model from modelscope
+#### 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 onnx --quantize false
```
-Export model from local path
+#### 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 /mnt/workspace/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize false
```
+#### Test onnx model
+Ref to [test](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export/test)
### Export torchscripts format model
-Export model from modelscope
+#### Export model from modelscope
```shell
-python -m funasr.export.export_model 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" false
+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
```
-Export model from local path
+#### 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" false
+python -m funasr.export.export_model --model-name /mnt/workspace/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type torch --quantize false
```
+#### Test onnx model
+Ref to [test](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export/test)
+
+## Runtime
+### ONNXRuntime
+#### ONNXRuntime-python
+Ref to [funasr-onnx](../../runtime/python/onnxruntime/README.md)
+#### ONNXRuntime-cpp
+Ref to [docs](../../runtime/readme.md)
+### Libtorch
+#### Libtorch-python
+Ref to [funasr-torch](../../runtime/python/libtorch/README.md)
+#### Libtorch-cpp
+Undo
+## Performance Benchmark
+
+### Paraformer on CPU
+
+[onnx runtime](../../runtime/docs/benchmark_onnx_cpp.md)
+
+[libtorch runtime](../../runtime/docs/benchmark_libtorch.md)
+
+### Paraformer on GPU
+[nv-triton](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/triton_gpu)
+
+
+## Acknowledge
+Torch model quantization is supported by [BladeDISC](https://github.com/alibaba/BladeDISC), an end-to-end DynamIc Shape Compiler project for machine learning workloads. BladeDISC provides general, transparent, and ease of use performance optimization for TensorFlow/PyTorch workloads on GPGPU and CPU backends. If you are interested, please contact us.
--
Gitblit v1.9.1