MarvinLvn / BabySLMLinks
Behavioral probing of language acquisition models at the lexical and syntactic level
☆17Updated 2 years ago
Alternatives and similar repositories for BabySLM
Users that are interested in BabySLM are comparing it to the libraries listed below
Sorting:
- Repository for multilingual speech data resources for native languages of Zambia.☆18Updated last year
- Implementation of the DIVA model of speech acquisition and production using PyTorch☆21Updated 2 years ago
- Keras-based python framework to compute phonological posterior probabilities from audio files☆43Updated 2 years ago
- ☆50Updated 5 months ago
- ☆14Updated 2 years ago
- Phoneme segmentation using pre-trained speech models☆55Updated 2 years ago
- Dataset of ICASSP 2021 MULTILINGUAL PHONETIC DATASET FOR LOW RESOURCE SPEECH RECOGNITION☆44Updated 2 years ago
- A multilingual phoneme recognizer capable of generalizing zero-shot to unseen phoneme inventories.☆26Updated 7 months ago
- Syllable Segmentation and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model☆34Updated 2 years ago
- Pypi installable TDNN and TDNN-F layers for PyTorch based acoustic model training☆41Updated 4 years ago
- MSP-Podcast Challenge Baseline Code☆26Updated last year
- fiwGAN/ciwGAN (Featural and Categorical InfoWaveGAN): Generative Adversarial Phonology and Semantics☆25Updated 2 years ago
- phone inventory library☆17Updated 2 years ago
- Speech-MASSIVE is a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSI…☆22Updated 3 weeks ago
- Confidence interval computation for evaluation in machine learning using the bootstrapping approach☆90Updated last year
- A unified dataset of multilingual emotional human utterances☆28Updated 3 years ago
- ☆40Updated 3 years ago
- A fasttrack implementation in python☆12Updated 5 months ago
- Grapheme-to-phoneme (G2P) conversion is the process of generating pronunciation for words based on their written form. It has a highly es…☆19Updated 4 years ago
- asr2k☆52Updated last year
- Simple Kaldi recipe for forced alignment☆11Updated 2 years ago
- SERAB: a multi-lingual benchmark for speech emotion recognition☆28Updated 2 years ago
- Keyword spotting and forced alignment in any language☆77Updated 2 months ago
- Phoneme alignment representation compatible with multiple forced aligners☆20Updated last year
- Deep Articulatory Synthesis and Inversion☆54Updated last year
- Transformer-based online speech recognition system with TensorFlow 2☆26Updated 4 years ago
- Workflow for forced alignment between languages☆21Updated last year
- Linguistic processing for Common Voice☆58Updated last year
- Phonetically-Oriented Word Error Rate☆36Updated 6 years ago
- DUSTED: Spoken-Term Discovery using Discrete Speech Units☆18Updated last year