sigmeta / g2p-kdLinks
Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion
☆20Updated 6 years ago
Alternatives and similar repositories for g2p-kd
Users that are interested in g2p-kd are comparing it to the libraries listed below
Sorting:
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 5 years ago
- ☆44Updated 5 years ago
- Chinese Text Normalization and Dataset☆87Updated 3 years ago
- Audio LPC (linear prediction code) using mel spectorgram, compatible for LPCNet☆62Updated 4 years ago
- Memory efficient transducer loss computation☆69Updated 3 years ago
- TTS Text Analyzer☆32Updated 2 years ago
- Implementation of the subscale framework from the WaveRNN paper, building on top of Fatchord's WaveRNN repo☆19Updated 5 years ago
- ☆76Updated 3 years ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆55Updated 3 months ago
- Pronunciation-assisted Subword Modeling☆31Updated 6 years ago
- multilingual speech aligner☆77Updated 2 years ago
- Materials accompanying the paper "Phonological features for 0-shot multilingual speech synthesis"☆33Updated 5 years ago
- pytorch CTC implementation for ASR. Use eesen's fst decoder framework☆10Updated 5 years ago
- it's ASR decoder and make graph project☆33Updated 3 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated 4 months ago
- ☆61Updated 2 years ago
- Linear Prediction Coefficients estimation from mel-spectrogram implemented in Python based on Levinson-Durbin algorithm.☆71Updated 4 years ago
- Neural network-based forced alignment with bidirectional attention mechanism☆78Updated 11 months ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 3 years ago
- [InterSpeech 2020] "Improving the Speaker Identity of Non-Parallel Many-to-Many VoiceConversion with Adversarial Speaker Recognition" by …☆39Updated 2 years ago
- ☆64Updated 3 years ago
- Predict prosody labels for Chinese sentences.☆41Updated 3 years ago
- Text frontend for ESPnet tts recipes☆34Updated 4 years ago
- A ctc decoder for both online and offline asr model☆66Updated 2 years ago
- Open Source Speech/Text Data on AI☆19Updated 3 years ago
- Multistream CNN for Robust Acoustic Modeling☆40Updated 4 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆59Updated 2 years ago
- ☆22Updated 6 years ago
- C++ implementation of End to End TTS which combines both Tacatron2 and LPCNET Vocoder.☆32Updated 6 years ago
- faster inference☆28Updated 11 months ago