Dataset
Lwazi
ANV
← All examples
Model summary →
Model
facebook/omniASR-CTC-1B
Open
10
facebook/omniASR-CTC-300M
Open
11
facebook/omniASR-CTC-3B
Open
8
facebook/omniASR-LLM-1B
Open
5
facebook/omniASR-LLM-300M
Open
6
facebook/omniASR-LLM-3B
Open
8
facebook/omniASR-LLM-7B
Open
5
dsfsi/anv-whisper-large-v3-turbo-anv-zul
Open
10
dsfsi/anv-whisper-small-anv-zulu-first-batch
Open
10
openai/whisper-large-v3
Open
43
openai/whisper-small
Open
26
sitwala/whisper-large-anv-sot
Open
53
sitwala/whisper-large-v3-anv-sot
Open
62
sitwala/whisper-large-v3-turbo-anv-zul-150h
Open
13
sitwala/whisper-large-v3-turbo-anv-zul-250h
Open
10
sitwala/whisper-large-v3-turbo-anv-zul-50h
Open
10
What did the model get wrong?
openai/whisper-small
Open
Example 99 of 100 · sample index 98
✅ What was actually said (isiZulu reference)
Ngingazama
umculo
we-jazz.
I-jazz
inezithako
eziningi,
futhi
iyahluka.
[um]
Kusukela
umculo
opholile,
kuze
kube
umculo
osezingeni
eliphezulu.
[um]
Ngingathokozela
nezinsimbi
ezahlukahlukene
futhi
umculo
ongangenza
ngizizwe
kahle.
🤖 What this model heard
ន្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្្
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
1
Wrong
25
Missed
0
Extra
0%
Words right
1.000
WER
1.000
CER
24.39s
Duration
0.3s
Latency