**Kana Whisper** is a fine-tuned Whisper large-v3-turbo model that transcribes Japanese speech directly into **katakana** sequences. This model is the ASR component of the Joyo Kanji Yomi Benchmark, a systematic evaluation framework for kanji-level reading accuracy of Japanese TTS systems. It was developed as part of the Sarashina2.2-TTS project, where it serves as the backbone of the **Kana CER** (Kana Character Error Rate) metric proposed in our paper.
译文排队中 · 当前显示来源原文
分类待补充
输入 待核验→ 输出 待核验
ModernBERT is a new variant of the BERT model that combines local and global attention, allowing it to handle long sequences while maintaining high computational efficiency. It also incorporates modern architectural improvements, such as RoPE. Our ModernBERT-Ja-130M is trained on a high-quality corpus of Japanese and English text comprising **4.39T tokens**, featuring a vocabulary size of 102,400 and a sequence length of **8,192** tokens. Additionally, if your GPUs support Flash Attention 2, we recommend using our models with Flash Attention 2.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 文本
This repository provides Japanese ModernBERT trained by SB Intuitions. Our ModernBERT-Ja-310M is trained on a high-quality corpus of Japanese and English text comprising **4.09T tokens**, featuring a vocabulary size of 102,400 and a sequence length of **8,192** tokens. Additionally, if your GPUs support Flash Attention 2, we recommend using our models with Flash Attention 2.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 向量
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 向量
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
分类待补充
输入 待核验→ 输出 待核验
This model has limited safety training. Therefore, it might generate some meaningless sequences, some inaccurate instances, or biased/objectionable outputs. Before using it, we would like developers to tune models based on human preferences and safety considerations.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
分类待补充
输入 待核验→ 输出 待核验
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
分类待补充
输入 待核验→ 输出 待核验
For detailed evaluation protocols, judge settings, prompt templates, and reproducible execution scripts, please refer to the flexeval evaluation manifest (in Japanese). This model has limited safety training. Therefore, it might generate some meaningless sequences, some inaccurate instances, or biased/objectionable outputs. Before using it, we would like developers to tune models based on human preferences and safety considerations.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 音频
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 文本
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 文本
This repository provides a tiny 16M parameters language model for debugging and testing purposes. The model was trained on English Wikipedia and Japanese Wikipedia to optimize a traditional language modelling objective for 25B tokens.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
This repository provides a tiny 16M parameters language model for debugging and testing purposes. This is created by tuning sbintuitions/tiny-lm with oasset1 datasets in Japanese and English. The model was first pre-trained on English Wikipedia and Japanese Wikipedia to optimize a traditional language modelling objective for 25B tokens. And then it was fine-tuned on oasst1 datasets in Japanese and English for 15 epochs.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
