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 · Data2vec-audio-large-960h9 results · 8 benchmarks
Model card

Data2vec-audio-large-960h.

unknown
§ 02 · Benchmarks

Every benchmark Data2vec-audio-large-960h has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01VoxPopuliSpeech · Speech Recognitionwer23.9%#5/55source ↗
02Earnings-22Speech · Speech Recognitionwer37.8%#6/50source ↗
03Open ASR LeaderboardSpeech · Speech Recognitionwer23.2%#7/52source ↗
04AMI-IHMSpeech · Speech Recognitionwer40.5%#8/50source ↗
05TED-LIUMSpeech · Speech Recognitionwer15.9%#9/50source ↗
06GigaSpeechSpeech · Speech Recognitionwer24.8%#10/47source ↗
07SPGISpeechSpeech · Speech Recognitionwer18.5%#10/56source ↗
08Open ASR LeaderboardSpeech · Speech Recognitionrtfx470.15#23/50source ↗
09LibriSpeechSpeech · Speech Recognitionwer12.9%#87/92source ↗
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 Data2vec-audio-large-960h actually performs.

Speech
8
benchmarks
avg rank #18.3
§ 04 · Papers

1 paper with results for Data2vec-audio-large-960h.

  1. 2022-02-07· 9 results

    data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

§ 06 · Sources & freshness

Where these numbers come from.

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