Dataset
Lwazi
ANV
← All examples
Model summary →
Model
facebook/omniASR-CTC-1B
Open
7
facebook/omniASR-CTC-300M
Open
9
facebook/omniASR-CTC-3B
Open
7
facebook/omniASR-CTC-7B
Open
5
facebook/omniASR-LLM-1B
Open
4
facebook/omniASR-LLM-300M
Open
4
facebook/omniASR-LLM-3B
Open
4
facebook/omniASR-LLM-7B
Open
2
aadel4/omniASR-CTC-1B-v2
Open
15
aadel4/omniASR-CTC-300M-v2
Open
7
badrex/w2v-bert-2.0-zulu-asr
Open
6
dsfsi/anv-whisper-large-v3-turbo-anv-zul
Open
5
dsfsi/anv-whisper-small-anv-zulu-first-batch
Open
8
facebook/mms-1b-all
Open
8
openai/whisper-large-v3
Open
14
openai/whisper-small
Open
11
sitwala/whisper-large-anv-sot
Open
19
sitwala/whisper-large-v3-anv-sot
Open
18
sitwala/whisper-large-v3-turbo-anv-zul-150h
Open
6
sitwala/whisper-large-v3-turbo-anv-zul-250h
Open
5
sitwala/whisper-large-v3-turbo-anv-zul-50h
Open
6
What did the model get wrong?
badrex/w2v-bert-2.0-zulu-asr
Open
Example 83 of 100 · sample index 82
✅ What was actually said (isiZulu reference)
kwaMerari
kwavela
umndeni
wa-
[n]
wamaHeli,
nomndeni,
wamaMushi
yileyo,
eyimindeni
yamaMerari.
🤖 What this model heard
kwamirari
kwavela
umndeni
kwamaheli
nomndeni
wama-mushi
yilelo
eyimindeni
yamamirari
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
5
Correct
4
Wrong
2
Missed
0
Extra
45%
Words right
0.700
WER
0.133
CER
10.02s
Duration
0.1s
Latency