whisper-tiny-cv11

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)

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.