whatmodel.sh / stt / SpeechBrain Conformer (LargeScaleASR / Loquacious)

SpeechBrain Conformer (LargeScaleASR / Loquacious)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

SpeechBrain Conformer (LargeScaleASR / Loquacious) is an open-weights speech-to-text model from SpeechBrain, released February 2025. Its published size is 0.48B parameters. Licence: apache-2.0.

Catalogue identity notes

CSV entry 'speechbrain/asr-conformer-largescaleasr' now redirects to speechbrain/asr-conformer-loquacious (dataset renamed LargeScaleASR -> Loquacious Set; weights unchanged since 2025-02, later commits are README only). Params: card '#params 480M'.

46.6±4.5#113 of 162 speech-to-text modelsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of SpeechBrain Conformer (LargeScaleASR / Loquacious), out of 176 with a score, then more from SpeechBrain.

#modelscorewhereRAMreleased
124CrisperWhisper Nyra Health47±3local~4.4GB2024-08
125VibeVoice-ASR-Streaming-7B Microsoft47±5local~17GB2026-09
126SpeechBrain Conformer (LargeScaleASR / Loquacious) SpeechBrain47±5local~2.8GB2025-02
127GigaAM Multilingual Large (CTC 600M) Sber47±7local~2.3GB2026-07
128STT En Conformer-Transducer Large NVIDIA46±4local~1.1GB2022-09
more from SpeechBrain
150SpeechBrain Transformer + TransformerLM (LibriSpeech) SpeechBrain40±7comparison only2022-03
157SpeechBrain wav2vec2 CTC (LibriSpeech) SpeechBrain35±4local~2GB2022-06

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests3 not in a task · 92% of its score
testresultvs the others in its rundifficultycountswhy
Open ASR English short-form WER (March 2026)8.5% ✎▁▁▁▃··▁▁▂██▆ beats 28/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 70%blunt
LibriSpeech test-other WER lab4.6% ✎▁▁▁▂▅▃▅▄█▂▂▁ beats 28/54avg 2.8%▇▇▇▇▇▇▇▇▇ 22%small run
VoxPopuli English test WER lab6.9% ✎█▄▄··████▄██ beats 6/16avg 7.4%—not counted yet: no other model in the same run to compare it with

$ where to run it

Other ways to run it

  1. Run it as published · needs ~2.8 GB · from huggingface.co/speechbrain (official)
    uv run --with speechbrain python -c "from speechbrain.inference.ASR import EncoderDecoderASR as A; print(A.from_hparams(source='speechbrain/asr-conformer-loquacious', savedir='pretrained_models/asr-conformer-loquacious').transcribe_file('audio.wav'))"

Official weights and documentation: huggingface.co/speechbrain ↗

$ how the score was worked out · Open ASR Leaderboard 70%, SpeechBrain Hugging Face ASR… 22%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Open ASR Leaderboard1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 70%Apache-2.0
SpeechBrain Hugging Face ASR model cards: published LibriSpeech/VoxPopuli WER for its own checkpoints · lab-reported1▇▇▇▇▇▇▇ 22%Apache-2.0
prior · pull toward the middle▇▇ 8%
weighted average= 46.6

not counted (1)

SpeechBrain Hugging Face ASR model cards: published LibriSpeech/VoxPopuli WER for its own checkpointsVoxPopuli English test WER [correct]6.9%fewer than three models have this test yet, or this source ran it for this model alone

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json