DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen6facebook/omniASR-CTC-300MOpen6facebook/omniASR-CTC-3BOpen0facebook/omniASR-LLM-1BOpen2facebook/omniASR-LLM-300MOpen3facebook/omniASR-LLM-3BOpen4facebook/omniASR-LLM-7BOpen2dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen4dsfsi/anv-whisper-small-anv-zulu-first-batchOpen0openai/whisper-large-v3Open35openai/whisper-smallOpen32sitwala/whisper-large-anv-sotOpen56sitwala/whisper-large-v3-anv-sotOpen58sitwala/whisper-large-v3-turbo-anv-zul-150hOpen4sitwala/whisper-large-v3-turbo-anv-zul-250hOpen4sitwala/whisper-large-v3-turbo-anv-zul-50hOpen4

What did the model get wrong?

openai/whisper-large-v3Open   Example 42 of 100  ·  sample index 41

✅ What was actually said (isiZulu reference)
WayengomunyewabaculibaseNingizimuAfrikaowayedumekakhulungesikhathisakhefuthiengumculiwe-hiphopwaseNingizimuAfrikaothengiswakakhulukunabobonke,futhiabaningibabemthathanjengomunyewabadlalibe-rapabakhulubaseNingizimuAfrika.
🤖 What this model heard
WaengumwunyewabakulibasennyingizimuAfrika.OwayetumegakulugizkatisakefutingumkuliwehiphopbasennyingizimuAfrika.Otengiswagakulukunabobonge.Futiabaningibabemtatanjengomwunyewabalaliberepu.AbakulubasennyingizimuAfrika.
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
5
Correct
22
Wrong
0
Missed
13
Extra
19%
Words right
1.370
WER
0.244
CER
26.81s
Duration
0.3s
Latency