fasr-asr-funasr

英文文档地址: README_EN.md

Fun-ASR-Nano 语音识别插件。该插件封装 funasr.AutoModel，把整段识别文本写入 AudioSpan.raw_text，不返回词级或字级时间戳。

安装

pip install fasr-asr-funasr

注册模型

默认 checkpoint 是 FunAudioLLM/Fun-ASR-Nano-2512。

流水线使用

from fasr import AudioPipeline

pipeline = (
    AudioPipeline()
    .add_pipe("detector", model="fsmn")
    .add_pipe(
        "recognizer",
        model="fun_asr_nano",
        device="cuda:0",
        language="中文",
        itn=True,
    )
    .add_pipe("sentencizer", model="ct_transformer")
)

Confection 配置

[asr_model]
@asr_models = "fun_asr_nano"
device = "cuda:0"
language = "中文"
itn = true
batch_size = 1

放在流水线里：

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

[pipeline.pipes]

[pipeline.pipes.recognizer]
@pipes = "thread_pipe"
batch_size = 4

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

[pipeline.pipes.recognizer.component.model]
@asr_models = "fun_asr_nano"
device = "cuda:0"
language = "中文"
itn = true
batch_size = 1

单独使用

from fasr.config import registry

model = registry.asr_models.get("fun_asr_nano")()
model.device = "cuda:0"

spans = model.transcribe(audio_spans, hotwords=["fasr"], language="中文")
for span in spans:
    print(span.text)

使用本地权重：

model.load_checkpoint("/path/to/Fun-ASR-Nano")

参数

输出

• 写入 span.raw_text。
• 不填充 span.tokens，因为 Fun-ASR-Nano 不返回时间戳。
• 读取 span.text 即可得到识别文本。

依赖

• fasr
• funasr
• Python 3.10-3.12