xinjli / transphone
phoneme tokenizer and grapheme-to-phoneme model for 8k languages
☆143Updated last year
Related projects ⓘ
Alternatives and complementary repositories for transphone
- Grapheme-to-Phoneme transductions that preserve input and output indices, and support cross-lingual g2p!☆134Updated this week
- ☆77Updated 5 months ago
- ☆110Updated 2 years ago
- UT-Sarulab MOS prediction system using SSL models☆183Updated 6 months ago
- Reference-aware automatic speech evaluation toolkit☆106Updated 8 months ago
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆179Updated 2 months ago
- Multilingual G2P in 100 languages☆285Updated last year
- multilingual speech aligner☆71Updated 11 months ago
- Byte-based multilingual transformer TTS for low-resource/few-shot language adaptation.☆89Updated 2 years ago
- Easy-to-Use Speech MOS predictors☆227Updated last year
- ☆161Updated 2 years ago
- Charsiu: A neural phonetic aligner.☆276Updated 2 years ago
- Unofficial implementation of miipher☆111Updated 6 months ago
- Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions☆217Updated 3 months ago
- Data and code for grapheme-to-phoneme transducers in lots of languages☆130Updated 7 months ago
- It's a repository for implementations of neural speech editing algorithms.☆191Updated 10 months ago
- Collection of pretrained models for the Montreal Forced Aligner☆113Updated 3 months ago
- PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling☆189Updated 2 years ago
- Official repository of DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech, ICASSP 2023☆202Updated last year
- A sequence-to-sequence voice conversion toolkit.☆85Updated 4 months ago
- a curated list of speech datasets (110+ datasets, 75+ easy to download)☆93Updated last year
- FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3☆166Updated 6 months ago
- This is the M-AILABS Speech Dataset☆16Updated 4 months ago
- This is the implementation for "ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Rhythm"☆127Updated 11 months ago
- Alignment files of LibriTTS.☆59Updated 4 years ago
- ☆40Updated 2 years ago
- ☆100Updated last month
- An official implementation of "UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"☆133Updated last year
- LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning☆114Updated 4 months ago
- Include Basis-MelGAN, MelGAN, HifiGAN and Multiband-HifiGAN, maybe NHV in the future.☆154Updated 3 years ago