
Code for training a speech recognition model using a Whisper decoder replaced with llm-jp-1.3b-v1.0.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
9
±0 (Oct 13〜)
Last commit
Sep 2024
Created on GitHub
Sep 7, 2024
Listed
Sep 10, 2024
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 9 |
| Jan 2026 | 9 |
| Feb 2026 | 9 |
| Mar 2026 | 9 |
| Apr 2026 | 9 |
| May 2026 | — |
| Jun 2026 | 9 |
| Jul 2026 | 9 |
| Aug 2026 | 9 |
| Sep 2026 | 9 |
| Oct 2026 | 9 |
| Nov 2026 | 9 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
whisper-asr-finetunesarulab-speech32Fine-tuning the Whisper ASR model.
N46WhisperAyanaminn1.7kWhisper based Japanese subtitle generator
OneCompressionFujitsuResearch445Post-training quantization (PTQ) pipeline for LLM developed by Fujitsu Laboratories. Integrated QEP (NeurIPS 2025), ILP mixed precision, pre-rotation processing, and vLLM plugin. Paper: arXiv:2603.28845.
easynovelassistantzuntan03237This is a simple novel generation assistant using the lightweight and unregulated Japanese local LLM "LightChatAssistant-TypeB". It generates forever with local privileges, stacking up hit gachas. It also supports reading aloud.
jparacrawl-finetuneMorinoseiMorizo104An example usage of JParaCrawl pre-trained Neural Machine Translation (NMT) models.
llm-lora-classificationhppRC97llm-lora-classification
Resources in similar research fields
- AnswerCarefullyllm-jp644AnswerCarefully Dataset supplies Japanese and multilingual data for commercial or non‑commercial LLM safety enhancement, prohibits any other use—including safety circumvention—allows derivative works with attribution, and carries a creator disclaimer of non‑liability for harms or service changes.HF datasetShared: Annotation and Dataset Development
- JGLUEllm-book546Dataset card for the JGLUE dataset used in the book “Large Language Model Introduction,” sourced from the original repo, with code licensed CC BY‑SA 4.0, data under the distributor’s license, citing Kurihara & Kawahara (in Japanese), and built on Shunsuke Kitada’s repository.HF datasetShared: Annotation and Dataset Development
- scaling-data-constrained-llmsllm-jp402A collection of Japanese and English web corpora—including a 9 B‑token Japanese set (JA‑WEB‑9B), 63 B‑token English and Japanese sets (EN‑WEB‑63B, JA‑WEB‑63B) and synthetic versions such as paraphrased JA‑PARAPHRASE‑63B, instruction‑style JA‑INSTRUCT‑63B, and translated JA‑TRANSLATE‑63B—used for studying data augmentation in pre‑training Japanese LLMs under data‑constrained settings.HF datasetShared: Annotation and Dataset Development
- Galgame_Speech_ASR_16kHzlitagin395Galgame_Speech_ASR_16kHz is a 16 kHz ASR dataset with 3.75 million pairs (≈5,354 h), derived from Galgame_Dataset, released under GPL v3.0 with commercial use prohibited and requiring any trained models to be open‑source (citation optional).HF datasetShared: Annotation and Dataset Development
- kaken-trans-ja-enhpprc358Japanese text from the kaken subset of llm-jp-corpus-v3 translated into English with Qwen/Qwen2.5‑32B‑Instruct, released as an open Japanese–English parallel corpus under a CC‑BY 4.0 license that inherits the original dataset’s terms.HF datasetShared: Annotation and Dataset Development
llm-jp-corpusllm-jp49This repository contains scripts to reproduce the LLM-jp corpus.Shared: Annotation and Dataset Development