DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen10facebook/omniASR-CTC-300MOpen11facebook/omniASR-CTC-3BOpen10facebook/omniASR-CTC-7BOpen11facebook/omniASR-LLM-1BOpen10facebook/omniASR-LLM-300MOpen9facebook/omniASR-LLM-3BOpen9facebook/omniASR-LLM-7BOpen10aadel4/omniASR-CTC-1B-v2Open10aadel4/omniASR-CTC-300M-v2Open11badrex/w2v-bert-2.0-zulu-asrOpen10dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen11dsfsi/anv-whisper-small-anv-zulu-first-batchOpen11facebook/mms-1b-allOpen12openai/whisper-large-v3Open17openai/whisper-smallOpen16sitwala/whisper-large-anv-sotOpen21sitwala/whisper-large-v3-anv-sotOpen203sitwala/whisper-large-v3-turbo-anv-zul-150hOpen11sitwala/whisper-large-v3-turbo-anv-zul-250hOpen10sitwala/whisper-large-v3-turbo-anv-zul-50hOpen10

What did the model get wrong?

facebook/omniASR-CTC-1BOpen   Example 59 of 100  ·  sample index 58

✅ What was actually said (isiZulu reference)
kwathiu-Israelesenama-esenamandla,[n]wawasebenzisa,[n][s]amaKhananikepha,[n]angiboni-kema-akawaxoshanganokuwaxosha.
🤖 What this model heard
kwathiuisraelesenama-esenamandlawabasebenzisaamakhananikephaangibonikemxoshwanganokuwaxosha
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
6
Correct
6
Wrong
4
Missed
0
Extra
38%
Words right
0.833
WER
0.140
CER
15.73s
Duration
0.2s
Latency