Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · Distil-large-v29 results · 8 benchmarks
Model card

Distil-large-v2.

unknown
§ 02 · Benchmarks

Every benchmark Distil-large-v2 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01TED-LIUMSpeech · Speech Recognitionwer4.9%#21/50source ↗
02VoxPopuliSpeech · Speech Recognitionwer8.2%#29/55source ↗
03Open ASR LeaderboardSpeech · Speech Recognitionwer7.9%#33/52source ↗
04GigaSpeechSpeech · Speech Recognitionwer10.3%#36/47source ↗
05SPGISpeechSpeech · Speech Recognitionwer3.3%#36/56source ↗
06Earnings-22Speech · Speech Recognitionwer12.2%#37/50source ↗
07Open ASR LeaderboardSpeech · Speech Recognitionrtfx202.95#37/50source ↗
08AMI-IHMSpeech · Speech Recognitionwer14.7%#42/50source ↗
09LibriSpeechSpeech · Speech Recognitionwer6.8%#73/92source ↗
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 Distil-large-v2 actually performs.

Speech
8
benchmarks
avg rank #38.2
§ 04 · Papers

1 paper with results for Distil-large-v2.

  1. 2023-11-01· 9 results

    Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
9
results
0 of 9 rows marked verified.