Whisper Small 24lang

--- license: apache-2.0 base_model: openai/whisper-small datasets: - burakaydinofficial/Whispered language: [en, de, es, fr, it, pt, ru, nl, pl, id, tr, hi, ms, sv, th, zh, cs, vi, fi, el, da, ja, "no", ko] pipeline_tag: automatic-speech-recognition library_name: transformers tags: [whisper, multilingual, speech-recognition, fine-tuned, control] --- # Whisper-Small-24Lang — 24 languages fine-tune, standard architecture (scientific control) A **plain `openai/whisper-small`** (unmodified architecture) fine-tuned on the 24 languages of the CC0 [Whispered](https://huggingface.co/datasets/burakaydinofficial/Whispered) corpus. This is the **matched scientific control** for [`burakaydinofficial/whisper-small-mla-24lang`](https://huggingface.co/burakaydinofficial/whisper-small-mla-24lang) — 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. ```python from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor model = AutoModelForSpeechSeq2Seq.from_pretrained("burakaydinofficial/whisper-small-24lang") # no trust_remote_code processor = AutoProcessor.from_pretrained("burakaydinofficial/whisper-small-24lang") ``` ## Reproduce the conversion cost Evaluate this control **and** `whisper-small-mla-24lang` on CommonVoice-17 (`scripts/validate.py` in the [code repo](https://github.com/burakaydinofficial/Whispered)); 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 | 12.2 WER | | de | 14.9 WER | | es | 10.0 WER | | fr | 19.1 WER | | it | 15.4 WER | | pt | 14.8 WER | | ru | 14.0 WER | | nl | 13.2 WER | | pl | 17.3 WER | | id | 19.5 WER | | tr | 21.1 WER | | hi | 23.2 WER | | ms | 20.1 WER | | sv-SE | 21.9 WER | | th | 12.1 CER | | zh-CN | 15.6 CER | | cs | 27.3 WER | | vi | 28.4 WER | | fi | 28.5 WER | | el | 30.5 WER | | da | 32.3 WER | | ja | 23.3 CER | | nn-NO | 43.1 WER | | ko | 44.2 WER | Encoder frozen during fine-tuning; 15,000 steps, warmup+cosine, fp16. Read-speech domain...