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 · Moonshine-tiny9 results · 8 benchmarks
Model card

Moonshine-tiny.

unknown
§ 02 · Benchmarks

Every benchmark Moonshine-tiny has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open ASR LeaderboardSpeech · Speech Recognitionrtfx753.06#10/50source ↗
02VoxPopuliSpeech · Speech Recognitionwer14.1%#13/55source ↗
03Earnings-22Speech · Speech Recognitionwer20.7%#14/50source ↗
04AMI-IHMSpeech · Speech Recognitionwer22.8%#15/50source ↗
05GigaSpeechSpeech · Speech Recognitionwer14.2%#15/47source ↗
06Open ASR LeaderboardSpeech · Speech Recognitionwer12.7%#15/52source ↗
07SPGISpeechSpeech · Speech Recognitionwer7.4%#15/56source ↗
08TED-LIUMSpeech · Speech Recognitionwer5.7%#18/50source ↗
09LibriSpeechSpeech · Speech Recognitionwer4.5%#56/92source ↗
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 Moonshine-tiny actually performs.

Speech
8
benchmarks
avg rank #19.0
§ 04 · Papers

1 paper with results for Moonshine-tiny.

  1. 2024-10-21· 9 results

    Moonshine: Speech Recognition for Live Transcription and Voice Commands

§ 06 · Sources & freshness

Where these numbers come from.

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