DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen7facebook/omniASR-CTC-300MOpen8facebook/omniASR-CTC-3BOpen4facebook/omniASR-LLM-1BOpen9facebook/omniASR-LLM-300MOpen6facebook/omniASR-LLM-3BOpen6facebook/omniASR-LLM-7BOpen5dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen4dsfsi/anv-whisper-small-anv-zulu-first-batchOpen5openai/whisper-large-v3Open10openai/whisper-smallOpen20sitwala/whisper-large-anv-sotOpen23sitwala/whisper-large-v3-anv-sotOpen24sitwala/whisper-large-v3-turbo-anv-zul-150hOpen3sitwala/whisper-large-v3-turbo-anv-zul-250hOpen4sitwala/whisper-large-v3-turbo-anv-zul-50hOpen4

What did the model get wrong?

facebook/omniASR-LLM-1BOpen   Example 16 of 100  ·  sample index 15

✅ What was actually said (isiZulu reference)
UMose,Greek,Moishe,Yiddish,Moshe,Hebrew,nomaiMovses,Armenian,yigamaelinikezweowesilisa,ngemuvakwesibaloseBhayibheliuMose.
🤖 What this model heard
umosegreekmosheyidishmushehebrewnomaimoshesarmenianyigamaelinikezweowesilisangemovakwesibhalosebhayibhiliumoshe
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
8
Correct
8
Wrong
0
Missed
1
Extra
50%
Words right
0.875
WER
0.147
CER
20.54s
Duration
1.4s
Latency