Model reference · open weights

kotoba-whisper-bilingual

Available as managed deployment Audio kotoba-tech Speech→text 1 variants 8k dl/mo

kotoba-whisper-bilingual is an open-weight audio or speech model from kotoba-tech. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bykotoba-tech
TypeAudio & music
TaskSpeech→text
Parameters (lead)756M
Runs withtransformers
Released2024-09-27
Popularity8k downloads / month
LicenceOpen weights

About

What kotoba-whisper-bilingual is

faster-whisper weight, whisper.cpp weight

Kotoba-Whisper-Bilingual is a collection of distilled Whisper models trained for

Read the full model card
  • Japanese ASR
  • English ASR
  • Speech-to-text translation (Japanese -> English)
  • Speech-to-text translation (English -> Japanese)

developed through the collaboration bewteen Asahi Ushio and Kotoba Technologies. Following the original work of distil-whisper (Robust Knowledge Distillation via Large-Scale Pseudo Labelling), we employ OpenAI's Whisper large-v3 as the teacher model for Japanese and English ASR, while we translate the transcription into English and Japanese by external LLM to obtain training dataset for speech-to-text translation. We employ ReazonSpeech for Japanese ASR and Japanese speech to English text translation, and Multilingual LibriSpeech for English ASR and English speech to Japanese text translation. Kotoba-whisper-bilingual's loss objective consists of cross-entropy on both of ASR and translation tasks, while KL divergence loss only for ASR task. The student model consists the full encoder of the teacher large-v3 model and the decoder with two layers initialized from the first and last layer of the large-v3 model.

As kotoba-whisper uses the same architecture as distil-whisper/distil-large-v3, it inherits the benefit of the improved latency compared to openai/whisper-large-v3 (6.3x faster than large-v3, see the table below taken from distil-whisper/distil-large-v3).

Evaluation

We compare our kotoba-whisper-bilingual with OpenAI whisper models, kotoba-whisper models, and cascaded models for translation. Worth noting that kotoba-whisper-bilingual is the only model that can do Japanese and English ASR and speech-to-text translation between Japanese and English, as OpenAI whisper is not trained for English to Japanese speech-to-text translation, and other models are specific to the Task (eg. kotoba-whisper is Japanese ASR and distil whisper is English ASR only).

Speech2Text Translation (Japanese->English): WER (smaller is better)

modelCoVoST2 (Ja->En)Fleurs (Ja->En)
kotoba-tech/kotoba-whisper-bilingual-v1.073.998.7
japanese-asr/ja-cascaded-s2t-translation (facebook/nllb-200-3.3B)64.367.1
japanese-asr/ja-cascaded-s2t-translation (facebook/nllb-200-1.3B)65.468.9
japanese-asr/ja-cascaded-s2t-translation (facebook/nllb-200-distilled-1.3B)65.667.4
japanese-asr/ja-cascaded-s2t-translation (facebook/nllb-200-distilled-600M)68.272.2
openai/whisper-large-v37186.1
[openai/whisper-large-v2]

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys kotoba-whisper-bilingual for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (kotoba-whisper-bilingual below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="kotoba-whisper-bilingual" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms