ASR-project / Multilingual-PRLinks
Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021) and WavLM (2022) pretrained on a corpus of English speech that we will use in various ways to perform phoneme recognition for different languages wi…
☆234Updated 3 years ago
Alternatives and similar repositories for Multilingual-PR
Users that are interested in Multilingual-PR are comparing it to the libraries listed below
Sorting:
- Charsiu: A neural phonetic aligner.☆307Updated 2 years ago
- Easy-to-Use Speech MOS predictors☆293Updated last year
- An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-S…☆407Updated last year
- PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean,…☆303Updated 3 years ago
- Official implementation of VQMIVC: One-shot (any-to-any) Voice Conversion @ Interspeech 2021 + Online playing demo!☆350Updated 3 years ago
- FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3☆206Updated last year
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆196Updated 9 months ago
- iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform☆254Updated 2 years ago
- Official implementation of Meta-StyleSpeech and StyleSpeech☆248Updated 3 years ago
- Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions☆259Updated 5 months ago
- Unofficial implementation of NaturalSpeech2 for Voice Conversion and Text to Speech☆236Updated last year
- Collection of pretrained models for the Montreal Forced Aligner☆155Updated 3 weeks ago
- PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised T…☆194Updated 2 years ago
- Update ASR paper everyday☆251Updated this week
- [INTERSPEECH 2024] The official implementation of EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for …☆156Updated last month
- UT-Sarulab MOS prediction system using SSL models☆244Updated last year
- Multilingual G2P in 100 languages☆333Updated 2 years ago
- Speaker embedding (d-vector) trained with GE2E loss☆282Updated last year
- This is the GitHub page for publicly available emotional speech data.☆356Updated 3 years ago
- Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)☆120Updated 3 years ago
- Segment an audio file and obtain utterance alignments. (Python package)☆337Updated last year
- PPG-Based Voice Conversion☆339Updated 2 years ago
- ☆120Updated 2 years ago
- It's a repository for implementations of neural speech editing algorithms.☆198Updated last year
- Official Implementation of StyleTTS-VC☆184Updated 5 months ago
- This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.☆590Updated last year
- ☆256Updated 2 years ago
- phoneme tokenizer and grapheme-to-phoneme model for 8k languages☆162Updated 2 years ago
- Unofficial implementation of NVIDIA P-Flow TTS paper☆225Updated 6 months ago
- JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech☆110Updated 3 years ago