DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen5facebook/omniASR-CTC-300MOpen7facebook/omniASR-CTC-3BOpen4facebook/omniASR-LLM-1BOpen8facebook/omniASR-LLM-300MOpen10facebook/omniASR-LLM-3BOpen7facebook/omniASR-LLM-7BOpen5dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen5dsfsi/anv-whisper-small-anv-zulu-first-batchOpen11openai/whisper-large-v3Open29openai/whisper-smallOpen29sitwala/whisper-large-anv-sotOpen31sitwala/whisper-large-v3-anv-sotOpen30sitwala/whisper-large-v3-turbo-anv-zul-150hOpen5sitwala/whisper-large-v3-turbo-anv-zul-250hOpen6sitwala/whisper-large-v3-turbo-anv-zul-50hOpen8

What did the model get wrong?

facebook/omniASR-LLM-3BOpen   Example 8 of 100  ·  sample index 7

✅ What was actually said (isiZulu reference)
ULouwSteytler,Usihlalowe-GrainSA,waxoxangokuhlanganaekulimeni,washofuthiukuthiukusebenzisanakuyisikhiyesokuphumelelakulomsebenziwokulima.
🤖 What this model heard
ulowstedlerusihlalowegrandasseywaxoxangokuhlanganaekulimeniwashofuthiukuthiukusebenzisanakuyisikhiyesokuphumelelakulomsebenziwokulima
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
11
Correct
5
Wrong
1
Missed
1
Extra
65%
Words right
0.529
WER
0.092
CER
16.24s
Duration
1.5s
Latency