Dataset
Lwazi
ANV
← All examples
Model summary →
Model
facebook/omniASR-CTC-1B
Open
7
facebook/omniASR-CTC-300M
Open
7
facebook/omniASR-CTC-3B
Open
5
facebook/omniASR-CTC-7B
Open
3
facebook/omniASR-LLM-1B
Open
4
facebook/omniASR-LLM-300M
Open
4
facebook/omniASR-LLM-3B
Open
3
facebook/omniASR-LLM-7B
Open
6
aadel4/omniASR-CTC-1B-v2
Open
4
aadel4/omniASR-CTC-300M-v2
Open
5
badrex/w2v-bert-2.0-zulu-asr
Open
2
dsfsi/anv-whisper-large-v3-turbo-anv-zul
Open
4
dsfsi/anv-whisper-small-anv-zulu-first-batch
Open
5
facebook/mms-1b-all
Open
4
openai/whisper-large-v3
Open
11
openai/whisper-small
Open
10
sitwala/whisper-large-anv-sot
Open
13
sitwala/whisper-large-v3-anv-sot
Open
14
sitwala/whisper-large-v3-turbo-anv-zul-150h
Open
3
sitwala/whisper-large-v3-turbo-anv-zul-250h
Open
3
sitwala/whisper-large-v3-turbo-anv-zul-50h
Open
5
What did the model get wrong?
facebook/omniASR-CTC-1B
Open
Example 84 of 100 · sample index 83
✅ What was actually said (isiZulu reference)
uma
kunje,
nawo
uMnyango
weMfundo,
ungeke
waphumelela,
ngamakomiti
awo.
🤖 What this model heard
uma
kanje
nawe
umnyanga
wemfundo
ungeke
waphumelele
la
ngamacomitee
hawu
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
3
Correct
6
Wrong
0
Missed
1
Extra
33%
Words right
0.889
WER
0.211
CER
7.71s
Duration
0.1s
Latency