Codesota · Models · CrisperWhispernyrahealth1 results · 1 benchmarks
Model card

CrisperWhisper.

nyrahealthopen-source1.5B paramsWhisper fine-tune with alignment
§ 02 · Benchmarks

Every benchmark CrisperWhisper has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01LibriSpeechSpeech · Speech Recognitionwer1.8%#8/92source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where CrisperWhisper actually performs.

Speech
1
benchmark
avg rank #8.0
§ 04 · Papers

1 paper with results for CrisperWhisper.

  1. 2024-08-29· 1 result

    CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
1
result
0 of 1 rows marked verified.