From 8a620a5a36df782e1f9e8cc56064d5dc6a1330b5 Mon Sep 17 00:00:00 2001
From: wanchen.swc <wanchen.swc@alibaba-inc.com>
Date: 星期三, 15 三月 2023 15:31:31 +0800
Subject: [PATCH] [Quantization] automatic mixed precision quantization
---
funasr/export/README.md | 26 +++++++++++++++++---------
1 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/funasr/export/README.md b/funasr/export/README.md
index a1ed892..33ab22e 100644
--- a/funasr/export/README.md
+++ b/funasr/export/README.md
@@ -11,35 +11,43 @@
`Tips`: torch>=1.11.0
```shell
- python -m funasr.export.export_model [model_name] [export_dir] [onnx] [quant]
+ python -m funasr.export.export_model \
+ --model-name [model_name] \
+ --export-dir [export_dir] \
+ --type [onnx, torch] \
+ --quantize \
+ --fallback-num [fallback_num]
```
- `model_name`: the model is to export. It could be the models from modelscope, or local finetuned model(named: model.pb).
+ `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.
+ `export-dir`: the dir where the onnx is export.
- `onnx`: `true`, export onnx format model; `false`, export torchscripts format model.
+ `type`: `onnx` or `torch`, export onnx format model or torchscript format model.
- `quant`: `true`, export quantized model at the same time; `false`, export fp32 model only.
+ `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.
+
## For example
### Export onnx format model
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 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 onnx
```
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 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 onnx
```
### Export torchscripts format model
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 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
```
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 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
```
--
Gitblit v1.9.1