Whisper-Tiny-CV11 — 11 languages fine-tune, standard architecture (scientific control)

A plain openai/whisper-tiny (unmodified architecture) fine-tuned on the 11 languages of the CC0 Whispered corpus. This is the matched scientific control for burakaydinofficial/whisper-tiny-mla-cv11 — trained identically, minus the MHA→MLA conversion — published so the MLA conversion cost is independently reproducible. No custom code: loads directly in transformers, and — being a plain unmodified Whisper — is convertible for faster-whisper / CTranslate2 / whisper.cpp via their standard converters.

from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
model = AutoModelForSpeechSeq2Seq.from_pretrained("burakaydinofficial/whisper-tiny-cv11")   # no trust_remote_code
processor = AutoProcessor.from_pretrained("burakaydinofficial/whisper-tiny-cv11")

Reproduce the conversion cost

Evaluate this control and whisper-tiny-mla-cv11 on CommonVoice-17 (scripts/validate.py in the code repo); the per-language difference is the conversion cost reported on the MLA card and in docs/results/.

Results (CommonVoice-17 test, greedy, Whisper normalization + Arabic folding; CER for th/zh/ja)

Lang	this control
en	26.6 WER
de	40.9 WER
es	28.3 WER
fr	43.4 WER
ru	39.5 WER
tr	51.1 WER
cy	86.7 WER
ar	65.9 WER
ka	122.6 WER
th	30.3 CER

Checkpoint note: this is the FINAL-step checkpoint; the dev-selected checkpoint that produced the reference numbers above was not retained, so an independent re-evaluation may differ by a few tenths of a WER point. The MLA card's reported cost used the dev-selected control.

Encoder frozen during fine-tuning; 15,000 steps, warmup+cosine, fp16. Read-speech domain (CommonVoice + FLEURS-validated). "Compression cost" does not apply to this unconverted control.