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 · Mms-1b-all9 results · 8 benchmarks
Model card

Mms-1b-all.

unknown
§ 02 · Benchmarks

Every benchmark Mms-1b-all has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01GigaSpeechSpeech · Speech Recognitionwer26.4%#5/47source ↗
02TED-LIUMSpeech · Speech Recognitionwer17.5%#5/50source ↗
03AMI-IHMSpeech · Speech Recognitionwer42.0%#7/50source ↗
04Open ASR LeaderboardSpeech · Speech Recognitionwer22.5%#11/52source ↗
05Earnings-22Speech · Speech Recognitionwer31.2%#12/50source ↗
06SPGISpeechSpeech · Speech Recognitionwer16.9%#12/56source ↗
07VoxPopuliSpeech · Speech Recognitionwer17.6%#12/55source ↗
08Open ASR LeaderboardSpeech · Speech Recognitionrtfx230.79#35/50source ↗
09LibriSpeechSpeech · Speech Recognitionwer12.6%#85/92source ↗
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 Mms-1b-all actually performs.

Speech
8
benchmarks
avg rank #20.4
§ 04 · Papers

1 paper with results for Mms-1b-all.

  1. 2023-05-22· 9 results

    Scaling Speech Technology to 1,000+ Languages

§ 06 · Sources & freshness

Where these numbers come from.

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