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 · Wav2vec2-large-960h-lv60-self9 results · 8 benchmarks
Model card

Wav2vec2-large-960h-lv60-self.

unknown
§ 02 · Benchmarks

Every benchmark Wav2vec2-large-960h-lv60-self has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Earnings-22Speech · Speech Recognitionwer31.7%#11/50source ↗
02SPGISpeechSpeech · Speech Recognitionwer17.9%#11/56source ↗
03VoxPopuliSpeech · Speech Recognitionwer21.4%#11/55source ↗
04AMI-IHMSpeech · Speech Recognitionwer36.8%#12/50source ↗
05GigaSpeechSpeech · Speech Recognitionwer23.9%#12/47source ↗
06Open ASR LeaderboardSpeech · Speech Recognitionwer21.3%#12/52source ↗
07TED-LIUMSpeech · Speech Recognitionwer14.9%#12/50source ↗
08Open ASR LeaderboardSpeech · Speech Recognitionrtfx509.32#19/50source ↗
09LibriSpeechSpeech · Speech Recognitionwer12.4%#81/92source ↗
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 Wav2vec2-large-960h-lv60-self actually performs.

Speech
8
benchmarks
avg rank #20.1
§ 04 · Papers

1 paper with results for Wav2vec2-large-960h-lv60-self.

  1. 2020-06-20· 9 results

    wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

§ 06 · Sources & freshness

Where these numbers come from.

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