fasr-punc-ct-transformer

英文文档地址: README_EN.md

CT-Transformer 标点恢复插件。通常作为 ASR 后面的 sentencizer 阶段，把无标点识别文本切成带标点的 AudioSpan 句子。

安装

pip install fasr-punc-ct-transformer

注册模型

默认 checkpoint 是 iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch。

流水线使用

from fasr import AudioPipeline

pipeline = (
    AudioPipeline()
    .add_pipe("detector", model="fsmn")
    .add_pipe("recognizer", model="paraformer")
    .add_pipe(
        "sentencizer",
        model="ct_transformer",
        disable_log=True,
        disable_pbar=True,
    )
)

Confection 配置

[punc_model]
@punc_models = "ct_transformer"
disable_update = true
disable_log = true
disable_pbar = true

放在流水线里：

[pipeline]
@pipelines = "AudioPipeline.v1"
pipe_order = ["sentencizer"]

[pipeline.pipes]

[pipeline.pipes.sentencizer]
@pipes = "thread_pipe"

[pipeline.pipes.sentencizer.component]
@components = "sentencizer"

[pipeline.pipes.sentencizer.component.model]
@punc_models = "ct_transformer"
disable_update = true
disable_log = true
disable_pbar = true

单独使用

from fasr.config import registry

model = registry.punc_models.get("ct_transformer")()
sentences = model.restore("今天天气真好我想出去玩你觉得呢")
for sentence in sentences:
    print(sentence.text)

参数

说明

• restore(text) 返回 AudioSpanList，不是普通字符串。
• 输入应是已经识别出来的文本；该插件不做 ASR。
• 流水线中应放在 sentencizer 组件上。

依赖

• fasr
• funasr
• Python 3.10-3.12