A fine‑tuned Whisper large‑v3‑turbo model that transcribes Japanese speech into katakana, serving as the ASR component of the Joyo Kanji Yomi Benchmark within the Sarashina2.2‑TTS project and powering the Kana CER Usage With Transformers pipeline.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
42,000
Hugging Face likes
21
Listed
Jun 30, 2026
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | — |
| Jan 2026 | — |
| Feb 2026 | — |
| Mar 2026 | — |
| Apr 2026 | — |
| May 2026 | — |
| Jun 2026 | 2,000 |
| Jul 2026 | 5,000 |
| Aug 2026 | 12,000 |
| Sep 2026 | 45,000 |
| Oct 2026 | 55,000 |
| Nov 2026 | 42,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- bert-base-japanese-char-v3tohoku-nlp130kJapanese‑language BERT‑Base (12 layers, 768‑dim, 12 heads) pretrained with Unidic‑based word‑level plus character‑level tokenization and whole‑word masking on CC‑100 and 2023 Wikipedia, producing a 7,027‑token vocabulary.
- bert-large-japanese-v2tohoku-nlp66kJapanese‑BERT‑Large trained on CC‑100 and Wikipedia, using Unidic‑lite word‑level tokenization with WordPiece subwords and whole‑word masking (24 layers, 1024‑dim hidden, 16 heads, 32k vocab), with pretraining code on cl‑tohoku/bert‑japanese.
- bert-base-japanese-v3tohoku-nlp66kJapanese BERT‑base (12 layers, 768‑dim hidden, 12 heads, 32 k vocab) pretrained with whole‑word masking on CC‑100 and 2023‑Jan Wikipedia, using Unidic 2.1.2 word‑level tokenization plus WordPiece, in 2 M training steps.
- t5-base-japanese-v1.1sonoisa17kA Japanese T5‑v1.1 model pretrained on ≈100 GB of Wikipedia and OSCAR CC‑100 data (mixed 10:1 for SentencePiece with byte‑fallback), requiring fine‑tuning for downstream tasks, includes transfer‑learning sample code, notes potential bias in outputs, and is licensed CC‑BY‑SA 4.0.
- deberta-v3-base-japaneseku-nlp13kJapanese DeBERTa V3 base pre‑trained on 540 B tokens from LLM‑jp v1.0, trained with a modified DeBERTa V3 setup, uses a unigram byte‑fallback tokenizer (no morphological analyzer), and is fine‑tuned for JGLUE NLU tasks.
- Moonlight-16B-A3B-Instruct-ggufmmnga7kA gguf-format release of moonshotai’s Moonlight‑16B‑A3B‑Instruct, trained on TFMC’s imatrix Japanese dataset, ready for use with llama.cpp (CUDA‑enabled) and shown by running a recipe‑request prompt.
Resources in similar research fields
- LFM2.5-Audio-1.5B-JP-GGUFLiquidAI506kQuantized GGUF versions of LiquidAI’s LFM 2.5‑Audio 1.5B JP model, including language, audio encoder, and vocoder weights (F32/F16/Q8_0/Q4_0), plus CLI/Server runners for ASR and TTS with llama.cpp.Shared: Speech recognition・Speech synthesis
sherpa-onnxk2-fsa15kSpeech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages.MultilingualShared: Speech recognition・Speech synthesis
moonshinemoonshine-ai11kVery low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces.MultilingualShared: Speech recognition・Speech synthesis
mlx-audioNeywa-Labs8kA text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.MultilingualShared: Speech recognition・Speech synthesis
FluidAudioFluidInference3kFrontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.MultilingualShared: Speech recognition・Speech synthesis
CrispASRCrispStrobe732C++ ggml runtime hub for multilingual ASR and TTS models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment, and more.MultilingualShared: Speech recognition・Speech synthesis