游雁
2023-04-27 30aa982bf29ceefaf52c0013c12c19adc57dea0e
egs_modelscope/punctuation/TEMPLATE/README.md
@@ -11,21 +11,21 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
inference_pipline = pipeline(
inference_pipeline = pipeline(
    task=Tasks.punctuation,
    model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
    model_revision=None)
rec_result = inference_pipline(text_in='example/punc_example.txt')
rec_result = inference_pipeline(text_in='example/punc_example.txt')
print(rec_result)
```
- text二进制数据,例如:用户直接从文件里读出bytes数据
```python
rec_result = inference_pipline(text_in='我们都是木头人不会讲话不会动')
rec_result = inference_pipeline(text_in='我们都是木头人不会讲话不会动')
```
- text文件url,例如:https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt
```python
rec_result = inference_pipline(text_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt')
rec_result = inference_pipeline(text_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt')
```
#### [CT-Transformer Realtime model](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727/summary)
@@ -52,15 +52,15 @@
Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/238)
#### API-reference
##### Define pipeline
### API-reference
#### Define pipeline
- `task`: `Tasks.punctuation`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `ngpu`: `1` (Default), decoding on GPU. If ngpu=0, decoding on CPU
- `output_dir`: `None` (Default), the output path of results if set
- `model_revision`: `None` (Default), setting the model version
##### Infer pipeline
#### Infer pipeline
- `text_in`: the input to decode, which could be:
  - text bytes, `e.g.`: "我们都是木头人不会讲话不会动"
  - text file, `e.g.`: example/punc_example.txt