DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen6facebook/omniASR-CTC-300MOpen6facebook/omniASR-CTC-3BOpen4facebook/omniASR-LLM-1BOpen3facebook/omniASR-LLM-300MOpen3facebook/omniASR-LLM-3BOpen2facebook/omniASR-LLM-7BOpen1dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen3dsfsi/anv-whisper-small-anv-zulu-first-batchOpen6openai/whisper-large-v3Open26openai/whisper-smallOpen40sitwala/whisper-large-anv-sotOpen47sitwala/whisper-large-v3-anv-sotOpen52sitwala/whisper-large-v3-turbo-anv-zul-150hOpen2sitwala/whisper-large-v3-turbo-anv-zul-250hOpen4sitwala/whisper-large-v3-turbo-anv-zul-50hOpen7

What did the model get wrong?

openai/whisper-smallOpen   Example 37 of 100  ·  sample index 36

✅ What was actually said (isiZulu reference)
Yizekungebonabonkeabesilisaabakhuluphelekakhuluabanesimosowesilisaesingcwatshiwe,abesilisaabangama-87percentabatholeukwelashwangokuhlinzwakwepipielingcwatshiwebabikwaukuthibakhuluphele.
🤖 What this model heard
Yīzegungimōnabongiabislīsaabakūlpēlegakōluabanisimōsōilīsaesingwajiwe.Abislīsaabangama87%abatoleuwelāshuangōgūtlīndwakwebībīelingwajiwebābīgwaugotībākūlpēle.
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
20
Wrong
0
Missed
20
Extra
0%
Words right
2.000
WER
0.446
CER
23.63s
Duration
0.3s
Latency