Dataset
Lwazi
ANV
← All examples
Model summary →
Model
facebook/omniASR-CTC-1B
Open
13
facebook/omniASR-CTC-300M
Open
10
facebook/omniASR-CTC-3B
Open
12
facebook/omniASR-CTC-7B
Open
14
facebook/omniASR-LLM-1B
Open
12
facebook/omniASR-LLM-300M
Open
11
facebook/omniASR-LLM-3B
Open
12
facebook/omniASR-LLM-7B
Open
12
aadel4/omniASR-CTC-1B-v2
Open
14
aadel4/omniASR-CTC-300M-v2
Open
17
badrex/w2v-bert-2.0-zulu-asr
Open
12
dsfsi/anv-whisper-large-v3-turbo-anv-zul
Open
9
dsfsi/anv-whisper-small-anv-zulu-first-batch
Open
16
facebook/mms-1b-all
Open
15
openai/whisper-large-v3
Open
17
openai/whisper-small
Open
17
sitwala/whisper-large-anv-sot
Open
17
sitwala/whisper-large-v3-anv-sot
Open
20
sitwala/whisper-large-v3-turbo-anv-zul-150h
Open
15
sitwala/whisper-large-v3-turbo-anv-zul-250h
Open
9
sitwala/whisper-large-v3-turbo-anv-zul-50h
Open
14
What did the model get wrong?
facebook/omniASR-CTC-300M
Open
Example 43 of 100 · sample index 42
✅ What was actually said (isiZulu reference)
oh
shagalolunye
la,
oh
angiboni
[n]
kahle
mos-
ngathi-
shagalolunye,
[n]
uNdasa
yini
[n]
u-
u-
March.
🤖 What this model heard
oh
shaga
lolunye
la
oh
angiboni
kahle
masingathi
shagalolunye
ondasa
yini
u
umaj
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
8
Correct
4
Wrong
5
Missed
1
Extra
47%
Words right
0.714
WER
0.169
CER
5.44s
Duration
0.2s
Latency