flyingshan / chinese_speech_feature_extraction
Spliting the ASR probability distribution results into the chinese pinyin, so as to extract more effective feature for the chinese speech.
☆21Updated last year
Related projects ⓘ
Alternatives and complementary repositories for chinese_speech_feature_extraction
- wav2lip in a Vector Quantized (VQ) space☆28Updated last year
- 复现Wav2Lip作者新的论文☆20Updated last year
- ☆27Updated last year
- SyncTalkFace: Talking Face Generation for Precise Lip-syncing via Audio-Lip Memory☆33Updated 2 years ago
- R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning☆78Updated 10 months ago
- Something about Talking Head Generation☆32Updated last year
- ☆30Updated 11 months ago
- ☆24Updated 3 years ago
- 📖 A curated list of resources dedicated to avatar.☆55Updated this week
- Optimized Syncnet and Chinese enhanced version, EN and CN checkpoints released☆13Updated 3 years ago
- [ICCV2023] Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video☆63Updated 7 months ago
- One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior, CVPRW 2024☆52Updated 2 weeks ago
- wav2lip训练数据预处理综合工具☆36Updated 11 months ago
- Psyche AI Inc release source "CVCUDA_FaceStoreHelper"☆66Updated last year
- A Real-Time High-Definition Teeth Restoration Network for ArbitraryTalking Face Generation Methods☆136Updated last year
- This is a project about talking faces. We use 576X576 sized facial images for training, which can generate 2k, 4k, 6k, and 8k digital hum…☆48Updated 7 months ago
- ☆73Updated last year
- Preprocessing Scipts for Talking Face Generation☆70Updated 3 months ago
- 这是一个在wav2lip，使用wav2lip、gfpgan、yolov5等模型用RT加速的超快推理！经测试在2070显卡上可达到0.03秒每帧实现实时推理。☆26Updated last year
- Project of "Adaptive Affine Transformation: A Simple and Effective Operation for Spatial Misaligned Image Generation"☆57Updated last year
- Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would t…☆59Updated last year
- ☆46Updated last year
- An optimized pipeline for DINet reducing inference latency for up to 60% 🚀. Kudos for the authors of the original repo for this amazing …☆102Updated last year
- This is the official source for our ACM MM 2023 paper "SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking …☆127Updated 11 months ago
- 基于DINet的推理服务，推理视频流和视频☆13Updated last year