DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen2facebook/omniASR-CTC-300MOpen2facebook/omniASR-CTC-3BOpen2facebook/omniASR-LLM-1BOpen2facebook/omniASR-LLM-300MOpen0facebook/omniASR-LLM-3BOpen0facebook/omniASR-LLM-7BOpen0dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen3dsfsi/anv-whisper-small-anv-zulu-first-batchOpen2openai/whisper-large-v3Open30openai/whisper-smallOpen36sitwala/whisper-large-anv-sotOpen44sitwala/whisper-large-v3-anv-sotOpen43sitwala/whisper-large-v3-turbo-anv-zul-150hOpen1sitwala/whisper-large-v3-turbo-anv-zul-250hOpen1sitwala/whisper-large-v3-turbo-anv-zul-50hOpen2

What did the model get wrong?

sitwala/whisper-large-anv-sotOpen   Example 12 of 100  ·  sample index 11

✅ What was actually said (isiZulu reference)
NgesikhathibefikaeZimbabweyanamuhla,umndeniwakwaMzilikaziwakwaKhumalo,owawuhlanganiswenezinyeizinhlanga,njengamaSuthu,amaTswanakanyenamanyeamaNgunisiaseNingizimuAfrika,ayaziwangokuthiamaNdebele.
🤖 What this model heard
kesekatsebefigaezembaboyanamohlaondenewakwamselekasewakwakomaloowahohlanganiswenezenyeezengtlangarenkamasothoamatswanakanyenamaneamangonesiasenengisemoafricaayaziwankobotsheamangdebeli
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
20
Wrong
0
Missed
24
Extra
0%
Words right
2.200
WER
0.371
CER
20.27s
Duration
0.3s
Latency