Dataset
Lwazi
ANV
← All examples
Model summary →
Model
facebook/omniASR-CTC-1B
Open
3
facebook/omniASR-CTC-300M
Open
2
facebook/omniASR-CTC-3B
Open
1
facebook/omniASR-LLM-1B
Open
2
facebook/omniASR-LLM-300M
Open
1
facebook/omniASR-LLM-3B
Open
2
facebook/omniASR-LLM-7B
Open
1
dsfsi/anv-whisper-large-v3-turbo-anv-zul
Open
1
dsfsi/anv-whisper-small-anv-zulu-first-batch
Open
2
openai/whisper-large-v3
Open
14
openai/whisper-small
Open
11
sitwala/whisper-large-anv-sot
Open
18
sitwala/whisper-large-v3-anv-sot
Open
22
sitwala/whisper-large-v3-turbo-anv-zul-150h
Open
2
sitwala/whisper-large-v3-turbo-anv-zul-250h
Open
2
sitwala/whisper-large-v3-turbo-anv-zul-50h
Open
2
What did the model get wrong?
openai/whisper-large-v3
Open
Example 43 of 100 · sample index 42
✅ What was actually said (isiZulu reference)
Kumele
futhi
siqinisekise
ukuthi
abalimi
bayasekelwa
baze
basimame
futhi
benze
inzuzo.
🤖 What this model heard
Kumele
foti
si
kini
segi
se
ugoti,
aba
limi
bayase
keli,
baze
basiman,
foti
benze
in
zozo.
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
3
Correct
8
Wrong
0
Missed
6
Extra
27%
Words right
1.273
WER
0.244
CER
11.29s
Duration
0.3s
Latency