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-fl1029 results · 8 benchmarks
Model card

Mms-1b-fl102.

unknown
§ 02 · Benchmarks

Every benchmark Mms-1b-fl102 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01AMI-IHMSpeech · Speech Recognitionwer86.8%#1/50source ↗
02Earnings-22Speech · Speech Recognitionwer51.9%#1/50source ↗
03GigaSpeechSpeech · Speech Recognitionwer42.4%#1/47source ↗
04Open ASR LeaderboardSpeech · Speech Recognitionwer39.8%#1/52source ↗
05TED-LIUMSpeech · Speech Recognitionwer32.4%#1/50source ↗
06SPGISpeechSpeech · Speech Recognitionwer26.2%#2/56source ↗
07VoxPopuliSpeech · Speech Recognitionwer28.0%#3/55source ↗
08Open ASR LeaderboardSpeech · Speech Recognitionrtfx234.42#33/50source ↗
09LibriSpeechSpeech · Speech Recognitionwer28.7%#92/92source ↗
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-fl102 actually performs.

Speech
8
benchmarks
avg rank #15.0
§ 04 · Papers

1 paper with results for Mms-1b-fl102.

  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.