Downloads · 30 days
12
6% of all-time downloads
burakaydinofficial/whisper-large-v3-mla-cv11
whisper-large-v3-mla-cv11 is a automatic speech recognition model from burakaydinofficial. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
openai/whisper-large-v3 with decoder self-attention converted MHA→MLA (Whisper-MLA, arXiv:2603.00563) and recovery-fine-tuned on the CC0 Whispered corpus — the same model that annotated that corpus, now with a 62.5% s…
Downloads · 30 days
12
6% of all-time downloads
All-time downloads
211
Public
Parameters
1.5B
3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3 GB · 100%
From the Hugging Face model README
openai/whisper-large-v3 with decoder self-attention converted MHA→MLA
(Whisper-MLA, arXiv:2603.00563) and recovery-fine-tuned on the
CC0 Whispered corpus — the same
model that annotated that corpus, now with a 62.5% smaller decode KV-cache. Conversion cost vs
an identically-trained unconverted control: not statistically significant on 9 of 11 languages
(significant only on ar +0.56 WER and zh +0.52 CER; median ≈ +0.1). n=1500/lang, paired per-speaker bootstrap.
from transformers import AutoModelForSpeechSeq2Seq
model = AutoModelForSpeechSeq2Seq.from_pretrained("burakaydinofficial/whisper-large-v3-mla-cv11", trust_remote_code=True) # transformers==4.46.x
| Lang | WER/CER % | conversion cost |
|---|---|---|
| en | 6.6 / 3.2 | +0.20 ns |
| de | 5.3 / 1.9 | +0.09 ns |
| es | 4.2 / 1.4 | +0.02 ns |
| fr | 9.6 / 3.6 | +0.08 ns |
| ru | 4.2 / 1.1 | −0.03 ns |
| tr | 8.4 / 1.9 | −0.08 ns |
| cy | 35.8 / 12.0 | +0.67 ns |
| ar | 16.6 / 6.0 | +0.56 ✱ |
| th | 14.0 / 4.4 | −0.02 CER ns |
| zh | 18.3 / 9.7 | +0.52 CER ✱ |
| ka | 72.3 / 34.3 | +0.22 ns — floor |
Size-scaling (measured across the released family): conversion cost falls with model size — tiny ≈+1.9 → base ≈+1.0 → small ≈+0.4 → medium ≈+0.4 → large ≈ 0 (approximate per-size medians; the exact per-language costs are in each model's table). We preregistered predictions twice and revised twice (decay → "saturation" → decay-to-zero); the monotone decline is the honest result.
Matched control now published — verify the conversion cost yourself: burakaydinofficial/whisper-large-v3-cv11 (trained identically, minus the MHA→MLA conversion). Evaluate both with scripts/validate.py.
trust_remote_code=True and transformers==4.46.x (custom MLA attention modules); not loadable in whisper.cpp / faster-whisper / CTranslate2.ABSOLUTE FLEURS numbers on a different read-speech corpus. Do NOT compare these per-language to the CommonVoice table above — the corpora differ in transcript normalization/orthography and speaker pools (e.g. Welsh reads easier on FLEURS, Georgian worse), so cross-corpus swings are corpus artifacts, not model behavior. The clean out-of-domain claim is the PAIRED MLA-vs-control cost (verified to be small on the small tier). Per-language absolute: en 8.0 · de 7.2 · es 5.8 · fr 8.5 · ru 9.5 · tr 10.8 · cy 33.5 · ar 13.2 · th 17.9 · zh-CN 10.0 · ka 87.7. (Full JSON: the release repo's eval artifacts.)