speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

bugfix python runtime

Browse Source
This commit is contained in:
游雁 2024-07-25 09:49:22 +08:00
parent 5851fc53cd
commit 060f57d03a
6 changed files with 243 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
funasr/datasets/audio_datasets/samplers.py
View File

@ -368,6 +368,7 @@ class CustomDistributedBufferDynamicBatchSampler(DistributedSampler):
self.batch_size_sample_max = kwargs.get("batch_size_sample_max", 200)
self.start_step = start_step
self.batch_num = 1
self.batch_size_scale_threshold = kwargs.get("batch_size_scale_threshold", 40.0)
if self.start_step > 0:
logging.info(f"Warning, start_step > 0, dataloader start from step: {self.start_step}")
# super().__init__(
@ -399,7 +400,13 @@ class CustomDistributedBufferDynamicBatchSampler(DistributedSampler):
continue
sample_length = 1 if self.batch_type == "example" else original_sample_length
potential_batch_length = max(max_len_in_batch, sample_length) * (len(batch) + 1)
if potential_batch_length <= self.batch_size and count < self.batch_size_sample_max:
potential_max_len_in_batch = max(max_len_in_batch, sample_length)
batch_size = (
self.batch_size * self.batch_size_scale_threshold / potential_max_len_in_batch
if potential_max_len_in_batch > self.batch_size_scale_threshold
else self.batch_size
)
if potential_batch_length <= batch_size and count < self.batch_size_sample_max:
batch.append(idx)
max_len_in_batch = max(max_len_in_batch, sample_length)
count += 1

205
runtime/python/onnxruntime/funasr_onnx.egg-info/PKG-INFO Normal file
View File

@ -0,0 +1,205 @@
Metadata-Version: 2.1
Name: funasr-onnx
Version: 0.4.1
Summary: FunASR: A Fundamental End-to-End Speech Recognition Toolkit
Home-page: https://github.com/alibaba-damo-academy/FunASR.git
Author: Speech Lab of DAMO Academy, Alibaba Group
Author-email: funasr@list.alibaba-inc.com
License: MIT
Keywords: funasr,asr
Platform: Any
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Description-Content-Type: text/markdown
# ONNXRuntime-python
## 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
# If you want to export .onnx file, you should install modelscope and funasr
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
```
or install from source code
```shell
git clone https://github.com/alibaba/FunASR.git && cd FunASR
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
```
## Inference with runtime
### Speech Recognition
#### Paraformer
```python
from funasr_onnx import Paraformer
from pathlib import Path
model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model = Paraformer(model_dir, batch_size=1, quantize=True)
wav_path = ['{}/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav'.format(Path.home())]
result = model(wav_path)
print(result)
```
- `model_dir`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `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
from pathlib import Path
model_dir = "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
wav_path = '{}/.cache/modelscope/hub/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav'.format(Path.home())
model = Fsmn_vad(model_dir)
result = model(wav_path)
print(result)
```
- `model_dir`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `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
from pathlib import Path
model_dir = "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
wav_path = '{}/.cache/modelscope/hub/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav'.format(Path.home())
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`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `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 = "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
model = CT_Transformer(model_dir)
text_in="跨境河流是养育沿岸人民的生命之源长期以来为帮助下游地区防灾减灾中方技术人员在上游地区极为恶劣的自然条件下克服巨大困难甚至冒着生命危险向印方提供汛期水文资料处理紧急事件中方重视印方在跨境河流问题上的关切愿意进一步完善双方联合工作机制凡是中方能做的我们都会去做而且会做得更好我请印度朋友们放心中国在上游的任何开发利用都会经过科学规划和论证兼顾上下游的利益"
result = model(text_in)
print(result[0])
```
- `model_dir`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `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 = "damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727"
model = CT_Transformer_VadRealtime(model_dir)
text_in = "跨境河流是养育沿岸|人民的生命之源长期以来为帮助下游地区防灾减灾中方技术人员|在上游地区极为恶劣的自然条件下克服巨大困难甚至冒着生命危险|向印方提供汛期水文资料处理紧急事件中方重视印方在跨境河流>问题上的关切|愿意进一步完善双方联合工作机制|凡是|中方能做的我们|都会去做而且会做得更好我请印度朋友们放心中国在上游的|任何开发利用都会经过科学|规划和论证兼顾上下游的利益"
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`: model_name in modelscope or local path downloaded from modelscope. If the local path is set, it should contain `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
Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/benchmark_onnx.md)
## Acknowledge
1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
2. We partially refer [SWHL](https://github.com/RapidAI/RapidASR) for onnxruntime (only for paraformer model).

20
runtime/python/onnxruntime/funasr_onnx.egg-info/SOURCES.txt Normal file
View File

@ -0,0 +1,20 @@
README.md
setup.py
funasr_onnx/__init__.py
funasr_onnx/paraformer_bin.py
funasr_onnx/paraformer_online_bin.py
funasr_onnx/punc_bin.py
funasr_onnx/sensevoice_bin.py
funasr_onnx/vad_bin.py
funasr_onnx.egg-info/PKG-INFO
funasr_onnx.egg-info/SOURCES.txt
funasr_onnx.egg-info/dependency_links.txt
funasr_onnx.egg-info/requires.txt
funasr_onnx.egg-info/top_level.txt
funasr_onnx/utils/__init__.py
funasr_onnx/utils/e2e_vad.py
funasr_onnx/utils/frontend.py
funasr_onnx/utils/postprocess_utils.py
funasr_onnx/utils/sentencepiece_tokenizer.py
funasr_onnx/utils/timestamp_utils.py
funasr_onnx/utils/utils.py

1
runtime/python/onnxruntime/funasr_onnx.egg-info/dependency_links.txt Normal file
View File

@ -0,0 +1 @@

8
runtime/python/onnxruntime/funasr_onnx.egg-info/requires.txt Normal file
View File

@ -0,0 +1,8 @@
librosa
onnxruntime>=1.7.0
scipy
numpy<=1.26.4
kaldi-native-fbank
PyYAML>=5.1.2
onnx
sentencepiece

1
runtime/python/onnxruntime/funasr_onnx.egg-info/top_level.txt Normal file
View File

@ -0,0 +1 @@
funasr_onnx