DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen11facebook/omniASR-CTC-300MOpen11facebook/omniASR-CTC-3BOpen11facebook/omniASR-LLM-1BOpen9facebook/omniASR-LLM-300MOpen10facebook/omniASR-LLM-3BOpen9facebook/omniASR-LLM-7BOpen5dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen10dsfsi/anv-whisper-small-anv-zulu-first-batchOpen11openai/whisper-large-v3Open26openai/whisper-smallOpen27sitwala/whisper-large-anv-sotOpen39sitwala/whisper-large-v3-anv-sotOpen43sitwala/whisper-large-v3-turbo-anv-zul-150hOpen12sitwala/whisper-large-v3-turbo-anv-zul-250hOpen10sitwala/whisper-large-v3-turbo-anv-zul-50hOpen12

What did the model get wrong?

sitwala/whisper-large-anv-sotOpen   Example 28 of 100  ·  sample index 27

✅ What was actually said (isiZulu reference)
I-Ohloneinikezaama-associatedegreesangu-61aholelaekudluliselenienyuvesinomaemisebenzinikanyenezinhlelozezitifiketizomsebenziezingaphezukwe-100ezinikezaukuqeqeshwakwamakhonoemisebenzi.
🤖 What this model heard
ealaoneennegezaamaassociateddegreesangho61aholelaeguhlwiseleneenyofesenomaemsebenzenekanyenyezengtleelozezetifigetezomsebenzeezingaphezohoa100ezennyezaokaqeshwawamakholoemsebenzene
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
2
Correct
18
Wrong
0
Missed
21
Extra
10%
Words right
1.950
WER
0.347
CER
23.52s
Duration
0.2s
Latency