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 · Niagara-38m-batch.en8 results · 8 benchmarks
Model card

Niagara-38m-batch.en.

unknown
§ 02 · Benchmarks

Every benchmark Niagara-38m-batch.en has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01TED-LIUMSpeech · Speech Recognitionwer5.7%#17/50source ↗
02GigaSpeechSpeech · Speech Recognitionwer12.6%#19/47source ↗
03Open ASR LeaderboardSpeech · Speech Recognitionwer8.9%#23/52source ↗
04VoxPopuliSpeech · Speech Recognitionwer8.7%#25/55source ↗
05Earnings-22Speech · Speech Recognitionwer12.1%#38/50source ↗
06AMI-IHMSpeech · Speech Recognitionwer15.9%#39/50source ↗
07SPGISpeechSpeech · Speech Recognitionwer3.1%#40/56source ↗
08LibriSpeechSpeech · Speech Recognitionwer9.3%#77/92source ↗
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 Niagara-38m-batch.en actually performs.

Speech
8
benchmarks
avg rank #34.8
§ 04 · Papers

1 paper with results for Niagara-38m-batch.en.

  1. 2026-02-19· 8 results

    Niagara Batch English SSM

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
8
results
0 of 8 rows marked verified.