Dataset
Lwazi
ANV
← All examples
Model summary →
Model
facebook/omniASR-CTC-1B
Open
14
facebook/omniASR-CTC-300M
Open
14
facebook/omniASR-CTC-3B
Open
13
facebook/omniASR-LLM-1B
Open
9
facebook/omniASR-LLM-300M
Open
10
facebook/omniASR-LLM-3B
Open
11
facebook/omniASR-LLM-7B
Open
9
dsfsi/anv-whisper-large-v3-turbo-anv-zul
Open
8
dsfsi/anv-whisper-small-anv-zulu-first-batch
Open
13
openai/whisper-large-v3
Open
24
openai/whisper-small
Open
23
sitwala/whisper-large-anv-sot
Open
38
sitwala/whisper-large-v3-anv-sot
Open
39
sitwala/whisper-large-v3-turbo-anv-zul-150h
Open
10
sitwala/whisper-large-v3-turbo-anv-zul-250h
Open
10
sitwala/whisper-large-v3-turbo-anv-zul-50h
Open
12
What did the model get wrong?
sitwala/whisper-large-anv-sot
Open
Example 96 of 100 · sample index 95
✅ What was actually said (isiZulu reference)
[um]
Izinhlelo
zesimo
sezulu
[um]
zenziwa
ngocwaningo
olunembile.
[um]
Ukubandakanywa
[um]
kwabaphulaphuli,
[um]
nezithulo
ezahluka
hlukene.
[um]
Kubalulekile
ukufundisa
ngempilo,
nokuxhumana
kahle.
🤖 What this model heard
e
zentlelo
ze
simose
zolo
e
zeng
tseoang
ho
twaneng
ho
o
lone
mbele
ho
kban
daranywa
e
kwaba
pola
poole
e
ne
zitholo
e
tsa
hloka
hlweng
e
koba
lekele
ho
fondisa
ngempelo
nong
kumana
ra
hle
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
22
Wrong
0
Missed
16
Extra
0%
Words right
1.727
WER
0.460
CER
18.35s
Duration
0.4s
Latency