codegram / calbert
Catalan ALBERT (A Lite BERT for self-supervised learning of language representations)
☆14Updated 4 years ago
Alternatives and similar repositories for calbert:
Users that are interested in calbert are comparing it to the libraries listed below
- Pre-production releases for Spacy in Catalan☆14Updated 3 years ago
- Deepspeech ASR Model for the Catalan Language☆17Updated 4 years ago
- Repository for subjective and objective evaluation of source separation algorithms☆12Updated 6 years ago
- docker for HF wav2vec2-sprint☆13Updated 4 years ago
- Forced Alignments for Common Voice☆31Updated 4 years ago
- Running Mozilla's implementation of Baidu DeepSpeech on Google Colaboratory☆16Updated 6 years ago
- Official source for Catalan Language Models and resources made within Aina project.☆23Updated last year
- Minimal module for computing audio spectrograms☆15Updated 6 years ago
- ☆15Updated 5 years ago
- Training BERT for punctuation task☆10Updated 4 years ago
- ☆17Updated 7 months ago
- ☆75Updated 3 years ago
- Experiments with Hugging Face 🔬 🤗☆44Updated 7 months ago
- GitHub repo for my Tensorflow World hackathon submission☆19Updated 2 years ago
- Collaborative audio annotation tool☆17Updated 2 years ago
- App to explore latent spaces of music collections☆33Updated 10 months ago
- 🦁 Nala is an agile open-source voice assistant framework (20+ actions).☆35Updated last year
- Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode☆111Updated 2 years ago
- Breaks a word into syllables using an LSTM-based neural network.☆19Updated last year
- Parallelized automatic corpus collection for ASR. Forked from https://github.com/EgorLakomkin/KTSpeechCrawler☆23Updated 4 years ago
- Acoustic and language models for minorised languages.☆26Updated 4 years ago
- Python code to reproduce the experiments presented in the paper Multilingual Music Genre Embeddings for Effective Cross-Lingual Music Ite…☆11Updated 4 years ago
- The RadioTalk dataset of talk radio transcripts☆58Updated 4 years ago
- Transcribing audio files using Hugging Face's implementation of Wav2Vec2 + "chain-linking" NLP tasks to combine speech-to-text with downs…☆31Updated 4 years ago
- Simple text to phonemes converter for multiple languages☆20Updated 2 years ago
- ☆32Updated 4 years ago
- ☆11Updated 3 years ago
- ☆30Updated 2 years ago
- Speech in Flax/JAX☆15Updated 2 years ago
- 24-hour Automatic Speech Recognition☆27Updated 3 years ago