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-base-960h9 results · 8 benchmarks
Model card

Wav2vec2-base-960h.

unknown
§ 02 · Benchmarks

Every benchmark Wav2vec2-base-960h has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01SPGISpeechSpeech · Speech Recognitionwer27.6%#1/56source ↗
02VoxPopuliSpeech · Speech Recognitionwer32.5%#1/55source ↗
03GigaSpeechSpeech · Speech Recognitionwer30.9%#2/47source ↗
04Open ASR LeaderboardSpeech · Speech Recognitionwer29.4%#2/52source ↗
05TED-LIUMSpeech · Speech Recognitionwer21.1%#2/50source ↗
06AMI-IHMSpeech · Speech Recognitionwer45.6%#3/50source ↗
07Earnings-22Speech · Speech Recognitionwer48.5%#3/50source ↗
08Open ASR LeaderboardSpeech · Speech Recognitionrtfx686.00#11/50source ↗
09LibriSpeechSpeech · Speech Recognitionwer12.5%#83/92source ↗
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-base-960h actually performs.

Speech
8
benchmarks
avg rank #12.0
§ 04 · Papers

1 paper with results for Wav2vec2-base-960h.

  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.