wangjia
25acf9db6e
横向对比云端 gummy 与本地开源模型(faster-whisper/SenseVoice/Paraformer)， 重点覆盖中英混说，产出准确率(CER/WER/MER)/速度(延迟/RTF)/资源(cpu/mem/模型大小) 对比报告。公共集(ASCEND/AISHELL/LibriSpeech)统一走 HF 适配器 + 自定义 JSONL manifest。 gummy 引擎对照 server/internal/asr/gummy.go 协议移植。 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
35 lines
1.4 KiB
TOML
35 lines
1.4 KiB
TOML
[project]
|
||
name = "dudu-asr-eval"
|
||
version = "0.1.0"
|
||
description = "dudu ASR 模型评估框架：横向对比云端 gummy 与本地开源模型（准确率/速度/资源）"
|
||
requires-python = ">=3.10"
|
||
|
||
# 核心依赖：评估管线本身（不含本地推理引擎，按需装 extras）
|
||
dependencies = [
|
||
"jiwer>=3.0", # CER/WER/MER 编辑距离
|
||
"soundfile>=0.12", # 读音频
|
||
"soxr>=0.3", # 重采样到 16k
|
||
"numpy>=1.24",
|
||
"psutil>=5.9", # 资源探针（cpu/mem）
|
||
"pyyaml>=6.0", # config.yaml
|
||
"websocket-client>=1.6", # gummy 云端 WS（对照 gummy.go 移植）
|
||
"opencc>=1.1", # 繁→简归一化（缺失时自动降级）
|
||
"jinja2>=3.1", # HTML 报告
|
||
"rich>=13.0", # 进度/表格
|
||
"datasets>=2.18", # 公共集（ASCEND/AISHELL/LibriSpeech）
|
||
"huggingface_hub>=0.20",
|
||
]
|
||
|
||
[project.optional-dependencies]
|
||
# 本地开源引擎按需安装，避免核心管线被重依赖拖累
|
||
whisper = ["faster-whisper>=1.0"] # CTranslate2，CPU-first
|
||
funasr = ["funasr>=1.0", "torch>=2.0", "torchaudio>=2.0"] # SenseVoice / Paraformer
|
||
all = ["faster-whisper>=1.0", "funasr>=1.0", "torch>=2.0", "torchaudio>=2.0"]
|
||
|
||
[project.scripts]
|
||
asr-eval = "asr_eval.cli:main"
|
||
|
||
[tool.setuptools.packages.find]
|
||
where = ["."]
|
||
include = ["asr_eval*"]
|