DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen10facebook/omniASR-CTC-300MOpen16facebook/omniASR-CTC-3BOpen9facebook/omniASR-LLM-1BOpen11facebook/omniASR-LLM-300MOpen11facebook/omniASR-LLM-3BOpen14facebook/omniASR-LLM-7BOpen8dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen7dsfsi/anv-whisper-small-anv-zulu-first-batchOpen14openai/whisper-large-v3Open27openai/whisper-smallOpen33sitwala/whisper-large-anv-sotOpen58sitwala/whisper-large-v3-anv-sotOpen56sitwala/whisper-large-v3-turbo-anv-zul-150hOpen9sitwala/whisper-large-v3-turbo-anv-zul-250hOpen9sitwala/whisper-large-v3-turbo-anv-zul-50hOpen16

What did the model get wrong?

facebook/omniASR-LLM-7BOpen   Example 44 of 100  ·  sample index 43

✅ What was actually said (isiZulu reference)
UsihlaloweSikhwamase-GBVF,uDktJudyDlamini,utheuxhasomalilwezinhlanganoeziyi-108izicelozazoeziphumeleleluyaqhubeka.ImininingwanemayelananehlandlaelilandelayolokufakwakweziceloizotholakalamaduzekwiwebhusayithiyeSikhwamase-GBVFku-www.gbvf.org.za
🤖 What this model heard
usihlalowesikhwamase-gbvfuudkjudidlaminiutheuxhasomalilwezinhlanganoeziyi-108izicelozazoeziphumeleleluyaqhubekaimininingwanemayelananehlandlaelilandelayolokufakwakweziceloizotholakalamaduzekwiwebhusayithiyesikhwamase-gbvfku-wwwgbvforgza
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
22
Correct
5
Wrong
0
Missed
3
Extra
81%
Words right
0.370
WER
0.037
CER
39.07s
Duration
1.5s
Latency