whatmodel.sh / stt / ESPnet Transformer 18-layer + RNN LM

ESPnet Transformer 18-layer + RNN LM

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

ESPnet Transformer 18-layer + RNN LM is an open-weights speech-to-text model from ESPnet, released July 2020. Licence: cc-by-4.0.

Catalogue identity notes

Exact LibriSpeech 960h recipe run, README lines 854–878. Published checkpoint linked by recipe authors; a compatible local command has not yet been verified. Decoder and checkpoint averaging are recorded per result. Architecture names do not denote a generic pretrained model.

Model information sources

· Weights licence ↗

41.5±3.9#135 of 162 speech-to-text modelsfrom 2 benchmark results across 1 source* 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 ESPnet Transformer 18-layer + RNN LM, out of 176 with a score, then more from ESPnet.

#modelscorewhereRAMreleased
146Vosk en-us 0.22 Alpha Cephei (Vosk)42±6local~16GB2021-10
147GigaAM Multilingual (CTC 220M) Sber42±7local~0.9GB2026-07
148ESPnet Transformer 18-layer + RNN LM ESPnet42±4local~1GB2020-07
149ABR asr-19m-v2-en Applied Brain Research41±5local~0.1GB2025-11
150SpeechBrain Transformer + TransformerLM (LibriSpeech) SpeechBrain40±7comparison only2022-03
more from ESPnet
112ESPnet HuBERT Large + Conformer + Transformer LM ESPnet50±4local~8GB2022-01
113ESPnet WavLM Large + Conformer + Transformer LM ESPnet50±4local~8GB2022-01
129ESPnet E-Branchformer (no LM) ESPnet46±4local~0.8GB2023-01

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

$ what it's good at

other tests2 not in a task · 94% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-other WER lab6.2% ✎█▃▃·▃▅·▅···▅ beats 3/11avg 3.7%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 73%typical
LibriSpeech test-clean WER lab2.5% ✎█··▃▃▅▅▃···▅ beats 3/11avg 1.9%▇▇▇▇▇▇▇▇ 21%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~1.02 GB · from github.com/espnet (official)
    uv run --python 3.12 --with espnet==202610.post2 --with espnet_model_zoo==0.1.11 --with librosa python -c "import librosa; from espnet2.bin.asr_inference import Speech2Text; asr=Speech2Text.from_pretrained('Shinji Watanabe/librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best', beam_size=20, ctc_weight=0.4, lm_weight=0.6); speech,_=librosa.load('audio.wav', sr=16000, mono=True); print(asr(speech)[0][0])"

Weights and documentation: zenodo.org ↗

$ how the score was worked out · ESPnet LibriSpeech ASR recipe… 94%

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
ESPnet LibriSpeech ASR recipe results (pinned September 2026) · lab-reported2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%Apache-2.0
prior · pull toward the middle▇▇ 6%
weighted average= 41.5

$ 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