From d5784e3444ff891b92c681d866f1d527a25cb299 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期日, 23 四月 2023 15:51:59 +0800
Subject: [PATCH] Merge pull request #404 from alibaba-damo-academy/main
---
funasr/runtime/python/onnxruntime/README.md | 189 +++++++++++++++++++++++++++++++++++++++--------
1 files changed, 156 insertions(+), 33 deletions(-)
diff --git a/funasr/runtime/python/onnxruntime/README.md b/funasr/runtime/python/onnxruntime/README.md
index 87510fa..ed3deb6 100644
--- a/funasr/runtime/python/onnxruntime/README.md
+++ b/funasr/runtime/python/onnxruntime/README.md
@@ -1,30 +1,31 @@
-## Using funasr with ONNXRuntime
+# ONNXRuntime-python
+
+## Export the model
+### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#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
+pip install torch-quant # Optional, for torchscript quantization
+pip install onnx onnxruntime # Optional, for onnx quantization
+```
+
+### 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. Export the model.
- - Command: (`Tips`: torch >= 1.11.0 is required.)
-
- 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 --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize False
- ```
- - `e.g.`, Export model from local path, the model'name must be `model.pb`.
- ```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 False
- ```
-
-
-2. Install the `funasr_onnx`
+## Install `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
@@ -35,25 +36,147 @@
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
-
```
-3. 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
+## Inference with runtime
- 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)
+### Speech Recognition
+#### Paraformer
+ ```python
+ from funasr_onnx import Paraformer
- wav_path = ['/nfs/zhifu.gzf/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']
+ model_dir = "./export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+ model = Paraformer(model_dir, batch_size=1, quantize=True)
- result = model(wav_path)
- print(result)
- ```
+ wav_path = ['./export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']
+
+ result = model(wav_path)
+ print(result)
+ ```
+- `model_dir`: the model path, which contains `model.onnx`, `config.yaml`, `am.mvn`
+- `batch_size`: `1` (Default), the batch size duration inference
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: wav formt file, support formats: `str, np.ndarray, List[str]`
+
+Output: `List[str]`: recognition result
+
+#### Paraformer-online
+
+### Voice Activity Detection
+#### FSMN-VAD
+```python
+from funasr_onnx import Fsmn_vad
+
+model_dir = "./export/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
+wav_path = "./export/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav"
+model = Fsmn_vad(model_dir)
+
+result = model(wav_path)
+print(result)
+```
+- `model_dir`: the model path, which contains `model.onnx`, `config.yaml`, `am.mvn`
+- `batch_size`: `1` (Default), the batch size duration inference
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: wav formt file, support formats: `str, np.ndarray, List[str]`
+
+Output: `List[str]`: recognition result
+
+
+#### FSMN-VAD-online
+```python
+from funasr_onnx import Fsmn_vad_online
+import soundfile
+
+
+model_dir = "./export/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
+wav_path = "./export/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav"
+model = Fsmn_vad_online(model_dir)
+
+
+##online vad
+speech, sample_rate = soundfile.read(wav_path)
+speech_length = speech.shape[0]
+#
+sample_offset = 0
+step = 1600
+param_dict = {'in_cache': []}
+for sample_offset in range(0, speech_length, min(step, speech_length - sample_offset)):
+ if sample_offset + step >= speech_length - 1:
+ step = speech_length - sample_offset
+ is_final = True
+ else:
+ is_final = False
+ param_dict['is_final'] = is_final
+ segments_result = model(audio_in=speech[sample_offset: sample_offset + step],
+ param_dict=param_dict)
+ if segments_result:
+ print(segments_result)
+```
+- `model_dir`: the model path, which contains `model.onnx`, `config.yaml`, `am.mvn`
+- `batch_size`: `1` (Default), the batch size duration inference
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: wav formt file, support formats: `str, np.ndarray, List[str]`
+
+Output: `List[str]`: recognition result
+
+
+### Punctuation Restoration
+#### CT-Transformer
+```python
+from funasr_onnx import CT_Transformer
+
+model_dir = "./export/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
+model = CT_Transformer(model_dir)
+
+text_in="璺ㄥ娌虫祦鏄吇鑲叉部宀镐汉姘戠殑鐢熷懡涔嬫簮闀挎湡浠ユ潵涓哄府鍔╀笅娓稿湴鍖洪槻鐏惧噺鐏句腑鏂规妧鏈汉鍛樺湪涓婃父鍦板尯鏋佷负鎭跺姡鐨勮嚜鐒舵潯浠朵笅鍏嬫湇宸ㄥぇ鍥伴毦鐢氳嚦鍐掔潃鐢熷懡鍗遍櫓鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦闂涓婄殑鍏冲垏鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒跺嚒鏄腑鏂硅兘鍋氱殑鎴戜滑閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛﹁鍒掑拰璁鸿瘉鍏奸【涓婁笅娓哥殑鍒╃泭"
+result = model(text_in)
+print(result[0])
+```
+- `model_dir`: the model path, which contains `model.onnx`, `config.yaml`, `am.mvn`
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: `str`, raw text of asr result
+
+Output: `List[str]`: recognition result
+
+
+#### CT-Transformer-online
+```python
+from funasr_onnx import CT_Transformer_VadRealtime
+
+model_dir = "./export/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727"
+model = CT_Transformer_VadRealtime(model_dir)
+
+text_in = "璺ㄥ娌虫祦鏄吇鑲叉部宀竱浜烘皯鐨勭敓鍛戒箣婧愰暱鏈熶互鏉ヤ负甯姪涓嬫父鍦板尯闃茬伨鍑忕伨涓柟鎶�鏈汉鍛榺鍦ㄤ笂娓稿湴鍖烘瀬涓烘伓鍔ｇ殑鑷劧鏉′欢涓嬪厠鏈嶅法澶у洶闅剧敋鑷冲啋鐫�鐢熷懡鍗遍櫓|鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦>闂涓婄殑鍏冲垏|鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒秥鍑℃槸|涓柟鑳藉仛鐨勬垜浠瑋閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑|浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛瑙勫垝鍜岃璇佸吋椤句笂涓嬫父鐨勫埄鐩�"
+
+vads = text_in.split("|")
+rec_result_all=""
+param_dict = {"cache": []}
+for vad in vads:
+ result = model(vad, param_dict=param_dict)
+ rec_result_all += result[0]
+
+print(rec_result_all)
+```
+- `model_dir`: the model path, which contains `model.onnx`, `config.yaml`, `am.mvn`
+- `device_id`: `-1` (Default), infer on CPU. If you want to infer with GPU, set it to gpu_id (Please make sure that you have install the onnxruntime-gpu)
+- `quantize`: `False` (Default), load the model of `model.onnx` in `model_dir`. If set `True`, load the model of `model_quant.onnx` in `model_dir`
+- `intra_op_num_threads`: `4` (Default), sets the number of threads used for intraop parallelism on CPU
+
+Input: `str`, raw text of asr result
+
+Output: `List[str]`: recognition result
## Performance benchmark
--
Gitblit v1.9.1