zbller / MecariLinks
☆36Updated 3 months ago
Alternatives and similar repositories for Mecari
Users that are interested in Mecari are comparing it to the libraries listed below
Sorting:
- Preferred Generation Benchmark☆90Updated 2 months ago
- J-Moshi: A Japanese Full-duplex Spoken Dialogue System☆287Updated 7 months ago
- 青空文庫振り仮名注釈付き音声コーパスのデータセット☆42Updated 10 months ago
- Browser-based chat UI for TinySwallow-1.5B that runs without API calls.☆129Updated last month
- 【2024年版】BERTによるテキスト分類☆30Updated last year
- Survey of audio language models☆62Updated 2 months ago
- ☆39Updated last year
- AivisSpeech Engine: AI Voice Imitation System - Text to Speech Engine☆141Updated last week
- The Remdis toolkit: Building advanced real-time multimodal dialogue systems with incremental processing and large language models☆102Updated 7 months ago
- ☆49Updated last year
- DeepLearningのAttentionモデルをPytorchの低レベルAPIを使って1から制作しようという試みのリポジトリです。☆72Updated last month
- Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch☆20Updated last year
- ☆149Updated 4 months ago
- ☆89Updated 2 years ago
- デジタル化資料OCRテキスト化事業において作成されたOCR学習用データセット☆74Updated last year
- ☆55Updated last year
- Tools to implement active inferring and pseudo-consciousness in LLM☆112Updated 2 years ago
- Alpaca-LoRAをlivedoorニュースコーパスでFineTuningさせるサンプルコード☆21Updated 2 years ago
- Python-based chat demo for TinySwallow-1.5B that works completely offline☆58Updated 11 months ago
- ☆31Updated last year
- ☆19Updated 3 months ago
- VOICEVOXのコア内で用いられているディープラーニングモデルの推論コード☆31Updated last month
- This project uses llama.cpp as an LLM server to perform inference and generate speech using Synthetic voice library☆22Updated last year
- 音声認識、文章生成、音声合成を使って対話するチャットボットアプリ☆48Updated 3 months ago
- Easily turn large English text datasets into Japanese text datasets using open LLMs.☆25Updated last year
- AI based singing voice synthesis☆37Updated last year
- ☆108Updated 6 months ago
- ☆13Updated 10 months ago
- DistilBERT model pre-trained on 131 GB of Japanese web text. The teacher model is BERT-base that built in-house at LINE.☆46Updated 2 years ago
- This is a repository for comparing voice changer results and searching datasets and trained models.☆30Updated 2 years ago