Dataset
Lwazi
ANV
← All examples
Model summary →
Model
facebook/omniASR-CTC-1B
Open
3
facebook/omniASR-CTC-300M
Open
4
facebook/omniASR-CTC-3B
Open
2
facebook/omniASR-CTC-7B
Open
4
facebook/omniASR-LLM-1B
Open
4
facebook/omniASR-LLM-300M
Open
4
facebook/omniASR-LLM-3B
Open
4
facebook/omniASR-LLM-7B
Open
5
aadel4/omniASR-CTC-1B-v2
Open
4
aadel4/omniASR-CTC-300M-v2
Open
4
badrex/w2v-bert-2.0-zulu-asr
Open
4
dsfsi/anv-whisper-large-v3-turbo-anv-zul
Open
4
dsfsi/anv-whisper-small-anv-zulu-first-batch
Open
3
facebook/mms-1b-all
Open
4
openai/whisper-large-v3
Open
9
openai/whisper-small
Open
8
sitwala/whisper-large-anv-sot
Open
11
sitwala/whisper-large-v3-anv-sot
Open
15
sitwala/whisper-large-v3-turbo-anv-zul-150h
Open
3
sitwala/whisper-large-v3-turbo-anv-zul-250h
Open
3
sitwala/whisper-large-v3-turbo-anv-zul-50h
Open
4
What did the model get wrong?
facebook/omniASR-LLM-3B
Open
Example 88 of 100 · sample index 87
✅ What was actually said (isiZulu reference)
insumansumane,
ejwayelek-,
ejwayelek-
nje,
lena
exoxa
ngokudabuka
kokufa.
🤖 What this model heard
insumansumani
eyejwayeleki
eyejwayeleki
nje
lena
ecoqa
ngokudabuka
kokufa
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
4
Correct
4
Wrong
0
Missed
0
Extra
50%
Words right
0.750
WER
0.178
CER
10.82s
Duration
0.3s
Latency