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 · Parakeet-tdt-0.6b-v26 results · 5 benchmarks
Model card

Parakeet-tdt-0.6b-v2.

unknown
§ 02 · Benchmarks

Every benchmark Parakeet-tdt-0.6b-v2 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open ASR LeaderboardSpeech · Speech Recognitionrtfx3386.02#7/50source ↗
02LibriSpeechSpeech · Speech Recognitionwer3.2%#31/92source ↗
03AMI-IHMSpeech · Speech Recognitionwer11.2%#44/50source ↗
04Earnings-22Speech · Speech Recognitionwer11.2%#44/50source ↗
05Open ASR LeaderboardSpeech · Speech Recognitionwer6.0%#46/52source ↗
06SPGISpeechSpeech · Speech Recognitionwer2.2%#53/56source ↗
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 Parakeet-tdt-0.6b-v2 actually performs.

Speech
5
benchmarks
avg rank #37.5
§ 04 · Papers

1 paper with results for Parakeet-tdt-0.6b-v2.

  1. 2023-04-13· 6 results

    Efficient Sequence Transduction by Jointly Predicting Tokens and Durations

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
6
results
0 of 6 rows marked verified.