DatasetLwaziANV

← All examples Model summary →

Modelfacebook/omniASR-CTC-1BOpen31facebook/omniASR-CTC-300MOpen33facebook/omniASR-CTC-3BOpen29facebook/omniASR-LLM-1BOpen27facebook/omniASR-LLM-300MOpen27facebook/omniASR-LLM-3BOpen26facebook/omniASR-LLM-7BOpen25dsfsi/anv-whisper-large-v3-turbo-anv-zulOpen29dsfsi/anv-whisper-small-anv-zulu-first-batchOpen38openai/whisper-large-v3Open51openai/whisper-smallOpen51sitwala/whisper-large-anv-sotOpen53sitwala/whisper-large-v3-anv-sotOpen59sitwala/whisper-large-v3-turbo-anv-zul-150hOpen31sitwala/whisper-large-v3-turbo-anv-zul-250hOpen30sitwala/whisper-large-v3-turbo-anv-zul-50hOpen29

What did the model get wrong?

openai/whisper-smallOpen   Example 72 of 100  ·  sample index 71

✅ What was actually said (isiZulu reference)
[um]Okokuqalakungadingekakubenemigomoecacile,okushukuthi[um][?]kumelekubenesinqumosokuthiubaniokhokhayo.Okwesibilikube[?]nohlelolokuphathaimali.[um]Kumelekubekweisabelomaliesicacile.[um]Three,[um]ukubuyazekanjalo,okushukuthi[um]kumelekuhlanganyelwenjaloukuze[um][?]bahlolisiseiy'ndleko.[um]Four,ukuxhumanakahle,[um]ukukhuluma[um]ngokuqhubekayongezidingozabo.
🤖 What this model heard
ḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍḍ
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
1
Wrong
50
Missed
0
Extra
0%
Words right
1.000
WER
1.000
CER
47.50s
Duration
0.3s
Latency