DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen6facebook/omniASR-CTC-300MOpen7facebook/omniASR-CTC-3BOpen7facebook/omniASR-LLM-1BOpen5facebook/omniASR-LLM-300MOpen7facebook/omniASR-LLM-3BOpen3facebook/omniASR-LLM-7BOpen3dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen4dsfsi/anv-whisper-small-anv-zulu-first-batchOpen8openai/whisper-large-v3Open38openai/whisper-smallOpen90sitwala/whisper-large-anv-sotOpen53sitwala/whisper-large-v3-anv-sotOpen65sitwala/whisper-large-v3-turbo-anv-zul-150hOpen4sitwala/whisper-large-v3-turbo-anv-zul-250hOpen5sitwala/whisper-large-v3-turbo-anv-zul-50hOpen7

What did the model get wrong?

openai/whisper-large-v3Open   Example 61 of 100  ·  sample index 60

✅ What was actually said (isiZulu reference)
Ngiyakhumbulangosukuengahambakhonaemziniwakithi.Kwakukhonaumoyaopholilefuthingizwaumuzwawokuthula.Ngithintaizihlahlaezindalafuthingakhumbulaizikhathingidlalakonala.Lokhukwanginikaumuzwangokuxhumananomndeniwamifuthiwangikhumbuzaukubalulekakwemvelo
🤖 What this model heard
Ngeakumbulangusuguingahambakonamzinuwagitu.Wakonaumoyopolilefuti,gizwaumuzwawaktula.Ngitindaizilalaizindalafutingeakumbulaizikatigilalakunala.Lokuuguanginigaumuzwawakumananumdenuwamifutikwangekumbuzakubalulegawemveli.
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
2
Correct
30
Wrong
0
Missed
8
Extra
6%
Words right
1.188
WER
0.271
CER
28.48s
Duration
0.4s
Latency