Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Comparison of espnet/owsm_ctc_v4_1B
1 modelespnetespnet/owsm_ctc_v4_1BRemove ×
What’s different1B parameters · 75 languages · Encoder: Whisper · Decoder: CTC
DateOct 17, 2026Discovered
Listed rateSee provider quotes
Provider endpoints0 endpoints →
AMI-Cleaned WER ↗English short-form; normalization unversioned11.1% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned10.31% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned9.29% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
LS Clean WER ↗English short-form; normalization unversioned2.11% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
LS Other WER ↗English short-form; normalization unversioned4.38% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
SPGISpeech WER ↗English short-form; normalization unversioned2.31% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
URGENT2024 WER ↗English short-form; normalization unversioned16.12% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
Voice Arena Monsoon WER ↗English short-form; normalization unversioned6.66% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned4.09% WER ↗espnet/owsm_ctc_v4_1BLeaderboard entry
Context window—
Max output—
Parameters1B
Audio inputSupported
TranscriptionSupported

Add another model

Search all models →