DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen8facebook/omniASR-CTC-300MOpen9facebook/omniASR-CTC-3BOpen8facebook/omniASR-LLM-1BOpen8facebook/omniASR-LLM-300MOpen10facebook/omniASR-LLM-3BOpen7facebook/omniASR-LLM-7BOpen6dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen5dsfsi/anv-whisper-small-anv-zulu-first-batchOpen6openai/whisper-large-v3Open38openai/whisper-smallOpen30sitwala/whisper-large-anv-sotOpen53sitwala/whisper-large-v3-anv-sotOpen59sitwala/whisper-large-v3-turbo-anv-zul-150hOpen8sitwala/whisper-large-v3-turbo-anv-zul-250hOpen6sitwala/whisper-large-v3-turbo-anv-zul-50hOpen6

What did the model get wrong?

facebook/omniASR-LLM-300MOpen   Example 90 of 100  ·  sample index 89

✅ What was actually said (isiZulu reference)
[um]Ngizophakamisaukuthi[um]kudalweisikhungo[um]sezemidlaloesinendawoyokudlala[um]imitholampilonensizayokufunda.[um]Ngizokhulumanabantuukuzengiqondeizidingozabo,ngibenezingxoxofuthinabantuabashaukuzengithumeleimiqondoyabo
🤖 What this model heard
ngizophakamisaukuthikudalweisikhungosezemidlaloesinendawoyokudlalaimtholampilonensizayokufundangizokhulumanabantuukuzengikondeizindingozabongibenezingxongxofuthinabantuabashaukuzengithumeleiminkondoyabo
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
20
Correct
5
Wrong
5
Missed
0
Extra
67%
Words right
0.400
WER
0.136
CER
23.65s
Duration
3.0s
Latency