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-conformer-rel-pos-large-960h-ft9 results · 8 benchmarks
Model card

Wav2vec2-conformer-rel-pos-large-960h-ft.

unknown
§ 02 · Benchmarks

Every benchmark Wav2vec2-conformer-rel-pos-large-960h-ft has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Earnings-22Speech · Speech Recognitionwer38.3%#5/50source ↗
02Open ASR LeaderboardSpeech · Speech Recognitionwer23.3%#5/52source ↗
03AMI-IHMSpeech · Speech Recognitionwer42.4%#6/50source ↗
04SPGISpeechSpeech · Speech Recognitionwer18.9%#8/56source ↗
05GigaSpeechSpeech · Speech Recognitionwer25.0%#9/47source ↗
06VoxPopuliSpeech · Speech Recognitionwer22.4%#10/55source ↗
07TED-LIUMSpeech · Speech Recognitionwer15.8%#11/50source ↗
08Open ASR LeaderboardSpeech · Speech Recognitionrtfx522.46#17/50source ↗
09LibriSpeechSpeech · Speech Recognitionwer12.4%#82/92source ↗
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-conformer-rel-pos-large-960h-ft actually performs.

Speech
8
benchmarks
avg rank #17.0
§ 04 · Papers

1 paper with results for Wav2vec2-conformer-rel-pos-large-960h-ft.

  1. 2020-10-11· 9 results

    fairseq S2T: Fast Speech-to-Text Modeling with fairseq

§ 06 · Sources & freshness

Where these numbers come from.

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