Atotti / miipher-2Links
Googleの音声復元モデルMiipher-2の再現実装の学習および推論コード。学習済みモデルも公開しています。
☆30Updated 5 months ago
Alternatives and similar repositories for miipher-2
Users that are interested in miipher-2 are comparing it to the libraries listed below
Sorting:
- ☆91Updated 2 months ago
- [ACL 2025] OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching☆43Updated 10 months ago
- PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind☆61Updated 3 months ago
- Official implementation for FlowSep☆68Updated 11 months ago
- MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows☆116Updated 3 months ago
- Compute WER and SER for speech recognition evaluation☆17Updated last week
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆92Updated 11 months ago
- ☆23Updated last year
- Text-To-Speech for NotebookLM☆35Updated 5 months ago
- SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer.☆113Updated last year
- semantic tokenizer for speech and music☆21Updated 5 months ago
- Unofficial implementation of ConvNeXt-TTS powered by lightning☆17Updated last year
- ☆103Updated 2 months ago
- ☆15Updated last month
- [EMNLP 2024] ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers☆124Updated 9 months ago
- AudioSR-Upsampling (any -> 48kHz)☆42Updated last year
- a lightweight voice conversion☆85Updated last year
- Official Code for ParrotTTS☆58Updated last year
- Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis☆27Updated 9 months ago
- Llasa Speed Up☆56Updated 6 months ago
- ☆19Updated last year
- A TTS Trained on Universal Audio.☆41Updated 6 months ago
- Official implementation of paper: Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis☆47Updated 3 months ago
- Code for the blog "Neural audio codecs: how to get audio into LLMs"☆139Updated 2 months ago
- Streaming Vocos☆29Updated 6 months ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆76Updated last year
- X-E-Speech: Joint Training Framework of Non-Autoregressive Cross-lingual Emotional Text-to-Speech and Voice Conversion☆109Updated last year
- Apply Score diffusion to improve speech signals recorded under various adverse conditions and distortions, including noise, reverberation…☆73Updated last year
- A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.☆64Updated last year
- GPT-style network for phonemization with durations of text☆68Updated last year