projectlucas / efficient_whisperLinks
Robust Speech Recognition via Large-Scale Weak Supervision
☆19Updated 2 years ago
Alternatives and similar repositories for efficient_whisper
Users that are interested in efficient_whisper are comparing it to the libraries listed below
Sorting:
- 44100Hz日本語音源に対応した PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor です。☆20Updated 2 years ago
- VITS2 using Phoneme-Level Japanese BERT☆13Updated last year
- 日本語音声に対して音素ラベルをアラインメントするためのツールです☆32Updated 2 months ago
- ☆10Updated 3 years ago
- Nue-ASR inference code by rinna Co., Ltd.☆35Updated last year
- JATTS: A modern, research-oriented Japanese Text-to-speech Open-sourced Toolkit☆36Updated 2 months ago
- 44100Hz日本語HuBERTに対応した QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion です。☆15Updated 2 years ago
- ☆34Updated 2 years ago
- ☆47Updated last year
- xvector model on jtubespeech☆45Updated last year
- ☆56Updated 6 months ago
- context labels and pronunciation data for JSUT corpus☆72Updated 3 years ago
- JVS (Japanese versatile speech) コーパスの自作のラベル☆31Updated 4 years ago
- ☆32Updated 2 years ago
- Multi-lingual AudioCaps☆11Updated last year
- tdmelodic for open-jtalk☆23Updated 3 years ago
- A Japanese accent dictionary generator☆118Updated last year
- DDPM-based Pitch Generation and Pitch Controllable Voice Synthesis.☆53Updated last year
- ☆15Updated 3 weeks ago
- HTS-style full-context labels for JSUT v1.1☆47Updated 4 years ago
- RWCP-SSD-Onomatopoeia☆23Updated 2 years ago
- ☆25Updated 11 months ago
- ディジタル信号処理(慶應義塾大学)☆29Updated 2 weeks ago
- Speech Segmentation Toolkit using Julius☆18Updated 3 years ago
- 44100Hz日本語音源に対応させた unofficial vits2-TTS implementation in pytorchです。☆23Updated last year
- A repository of Japanese Phoneme-Level BERT☆22Updated last year
- pyopenjtalk-plus: A Python wrapper for OpenJTalk with additional improvements☆44Updated last month
- A Python package of the dynamic compressive gammachirp filterbank (dcGC-FB)☆28Updated last year
- 44100Hz日本語音源に対応した MB-iSTFT-VITS: Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Tim…☆37Updated 2 years ago
- Speech Segmentation Toolkit using Julius☆95Updated 5 years ago