DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen5facebook/omniASR-CTC-300MOpen6facebook/omniASR-CTC-3BOpen6facebook/omniASR-CTC-7BOpen5facebook/omniASR-LLM-1BOpen7facebook/omniASR-LLM-300MOpen6facebook/omniASR-LLM-3BOpen7facebook/omniASR-LLM-7BOpen7aadel4/omniASR-CTC-1B-v2Open8aadel4/omniASR-CTC-300M-v2Open7badrex/w2v-bert-2.0-zulu-asrOpen8dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen7dsfsi/anv-whisper-small-anv-zulu-first-batchOpen11facebook/mms-1b-allOpen7openai/whisper-large-v3Open14openai/whisper-smallOpen14sitwala/whisper-large-anv-sotOpen25sitwala/whisper-large-v3-anv-sotOpen25sitwala/whisper-large-v3-turbo-anv-zul-150hOpen7sitwala/whisper-large-v3-turbo-anv-zul-250hOpen6sitwala/whisper-large-v3-turbo-anv-zul-50hOpen8

What did the model get wrong?

facebook/omniASR-LLM-300MOpen   Example 55 of 100  ·  sample index 54

✅ What was actually said (isiZulu reference)
[s][n]kuko-kukhonaokuthileokubi,ezikuqondilengales-ngalelisu,lazolamazwi,uyawacabangaakazeawaphimisela.
🤖 What this model heard
kukho-kukhonaokuthileokubiezikuqondilengalesingalesilazolamazwiuyawacabangaakazeawaphinisela
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
8
Correct
4
Wrong
2
Missed
0
Extra
57%
Words right
0.500
WER
0.093
CER
13.02s
Duration
0.7s
Latency