feat(eval): ASR 模型评估框架
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>
This commit is contained in:
@@ -0,0 +1,14 @@
|
||||
# 数据集、模型权重、结果、缓存全部不入库(体积大)
|
||||
# 注意:锚定到 eval/ 根(前导 /),否则会误伤 asr_eval/datasets/ 源码包
|
||||
/datasets/
|
||||
/models/
|
||||
/results/
|
||||
*.wav
|
||||
*.mp3
|
||||
*.flac
|
||||
*.aiff
|
||||
__pycache__/
|
||||
*.egg-info/
|
||||
.venv/
|
||||
venv/
|
||||
.pytest_cache/
|
||||
Reference in New Issue
Block a user