shahruk10 / kaldi-tflite
Convert kaldi feature extraction and nnet3 models into Tensorflow Lite models. Currently aimed at converting kaldi's x-vector models and diarization pipelines to tensorflow models.
☆20Updated last year
Related projects: ⓘ
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆47Updated 2 months ago
- A light-weight Python library for computing Kaldi-style acoustic features based on NumPy☆14Updated 4 years ago
- Yin pitch estimator in PyTorch☆113Updated last year
- Production first, nn-based on-device signal processing toolkit.☆63Updated last year
- End-to-End Keyword Spotting (E2E-KWS) using a character level LSTM☆37Updated last year
- Implementation of audio degradation processes☆100Updated 8 years ago
- Linear Prediction Coefficients estimation from mel-spectrogram implemented in Python based on Levinson-Durbin algorithm.☆67Updated 3 years ago
- Pytorch implementation of subband decomposition☆88Updated 2 years ago
- Official implementation of "PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords" (INTERSPEECH 2023)☆35Updated 3 months ago
- A simple package for Guided source separation (GSS)☆104Updated 4 months ago
- Clustering-based methods for overlapping diarization☆68Updated 8 months ago
- python wrapper for kaldi's native I/O☆27Updated 5 months ago
- Multipurpose Multi Speaker Mixture Signal Generator☆43Updated 6 months ago
- MultiSV: scripts for data preparation☆24Updated 3 months ago
- Y-vector: Multiscale Waveform Encoder for Speaker Embedding☆24Updated 2 months ago
- Python package for combining diarization system outputs.☆73Updated 11 months ago
- Multi-Task Audio Source Separation, Two-Stage Model, Complex Domain.☆86Updated last year
- [InterSpeech 2020] "Improving the Speaker Identity of Non-Parallel Many-to-Many VoiceConversion with Adversarial Speaker Recognition" by …☆39Updated last year
- ☆50Updated 3 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- ☆75Updated 2 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 4 years ago
- NOTSOFAR-1 Challenge: Distant Diarization and ASR☆40Updated this week
- Segment a given audio into utterances using a trained end-to-end ASR model.☆73Updated 3 years ago
- C++ implementation of End to End TTS which combines both Tacatron2 and LPCNET Vocoder.☆31Updated 4 years ago
- Convert WSJ sphere format to waveform and do data simulation.☆16Updated 4 years ago
- ☆54Updated 3 years ago
- ☆48Updated 11 months ago
- Sequence-to-sequence TTS based on Kyubyong's dc_tts☆60Updated last year
- ☆63Updated last year