# dudu ASR 评估配置。改这里即可调整跑哪些引擎/数据集、采样多少。 # 跑法:rbw get dashscope-api-key | python -m asr_eval run --config config.yaml output_dir: results audio_cache: datasets/_audio_cache sample_limit: null # null=全量;整数=每个数据集采样上限(冒烟用小值) # ---------------- 数据集 ---------------- # 公共集统一走 type=hf(差异全在配置里);自定义集 type=custom 指向 JSONL manifest。 datasets: - name: ascend # 中英混说金标准(headline) type: hf hf_id: CAiRE/ASCEND split: test text_field: transcription lang: zh-en domain: general - name: aishell1 # 纯普通话 type: hf hf_id: AISHELL/AISHELL-1 split: test text_field: text lang: zh domain: general trust_remote_code: true - name: librispeech # 纯英文 type: hf hf_id: openslr/librispeech_asr hf_config: clean split: test text_field: text lang: en domain: general trust_remote_code: true - name: custom # 你的自录/业务场景音频 type: custom manifest: manifests/custom.example.jsonl # ---------------- 引擎 ---------------- # 云端 gummy 与本地开源横向对比。本地引擎需先装 extras:pip install '.[whisper]' 或 '.[funasr]' engines: - name: gummy type: gummy model: gummy-realtime-v1 realtime_factor: 2.0 # 推流倍速(同 gummycheck);影响延迟口径,不影响准确率 cost_per_min: 0.09 # ⚠️占位:按 dudu 实付 DashScope 单价改(此处暂用售价 ¥9/100min) enabled: true - name: whisper-small type: whisper model_size: small device: cpu compute_type: int8 enabled: true - name: whisper-large-v3 type: whisper model_size: large-v3 device: cpu compute_type: int8 enabled: false # 体积大(~1.5GB),按需开 - name: sensevoice type: sensevoice # 多语,中英混说强 device: cpu enabled: false - name: paraformer-zh type: funasr # 纯中 SOTA,英文/混说较弱 device: cpu enabled: false