
Fine-tuning the Whisper ASR model.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
32
±0 (Oct 13〜)
Last commit
Dec 2022
Created on GitHub
Oct 27, 2022
Listed
Oct 29, 2022
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 32 |
| Jan 2026 | 32 |
| Feb 2026 | 32 |
| Mar 2026 | 32 |
| Apr 2026 | 32 |
| May 2026 | 32 |
| Jun 2026 | 32 |
| Jul 2026 | 32 |
| Aug 2026 | 32 |
| Sep 2026 | 32 |
| Oct 2026 | 32 |
| Nov 2026 | 32 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
llm-jp-asrtosiyuki9Code for training a speech recognition model using a Whisper decoder replaced with llm-jp-1.3b-v1.0.
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
- wav2vec2-large-xlsr-53-japanesejonatasgrosman16MJapanese wav2vec‑2 XLSR‑53 fine‑tuned on Common Voice 6.1, CSS10, and JSUT, requiring 16 kHz audio and usable via HuggingSound or HuggingFace pipelines.HF modelShared: Text Generation・Language Models
- kotoba-whisper-v2.2kotoba-tech16kKotoba‑Whisper‑v2.2 is a Japanese ASR model extending kotoba‑whisper‑v2.0 with integrated diarization and automatic punctuation via a HuggingFace‑Transformers pipeline, built in collaboration with Asahi Ushio and Kotoba Technologies.HF modelShared: Language Models・Speech & Audio in NLP
asrzakuro-ai72Automatic Speech Recognition with deepspeech2 model in pytorch with support from Zakuro AI.Shared: Speech Recognition・Text Generation- parakeet-tdt_ctc-0.6b-janvidia7kNVIDIA NeMo’s 0.6 B‑parameter Hybrid FastConformer‑TDT‑CTC ASR model transcribes Japanese speech with punctuation and is available for inference or fine‑tuning within the NeMo framework.HF modelShared: Text Generation・Speech & Audio in NLP
- japanese-anime-speechjoujiboi946Japanese Anime Speech Dataset offers 73,004 audio‑text pairs (110 hours total, evolving from V1 to V5) to enhance ASR models such as OpenAI’s Whisper, available under an open license for all uses with credit appreciated.HF datasetShared: Speech Recognition・Text Generation
- gpt-neox-japanese-2.7babeja3kA 2.7‑B‑parameter Japanese GPT‑NeoX model trained on Japanese CC‑100 and OSCAR by ABEJA Inc, usable via Hugging Face Transformers pipelines or PyTorch and released under the MIT license.HF modelShared: Text Generation・Language Models