zouharvi / pwesuiteLinks
Suite for phonetic word embeddings, especially their evaluation and baseline models.
☆31Updated 6 months ago
Alternatives and similar repositories for pwesuite
Users that are interested in pwesuite are comparing it to the libraries listed below
Sorting:
- Datasets for turn-taking research☆15Updated last year
- vad☆20Updated 2 years ago
- ☆34Updated 4 years ago
- A guide to building language technology in new languages.☆59Updated 3 years ago
- Universal Romanizer that can convert any unicode script to roman (latin) script☆219Updated last year
- Grapheme-to-Phoneme transductions that preserve input and output indices, and support cross-lingual g2p!☆173Updated last week
- ☆56Updated 2 years ago
- A merged version of multiple open-source German speech datasets.☆33Updated last year
- phone inventory library☆16Updated 2 years ago
- Promting Whisper for Audio-Visual Speech Recognition, Code-Switched Speech Recognition, and Zero-Shot Speech Translation☆148Updated last year
- phoneme tokenizer and grapheme-to-phoneme model for 8k languages☆169Updated 2 years ago
- Script to train a German n-gram Language Model on articles of Wikipedia☆13Updated 6 years ago
- Universal multilingual automatic speech transcription into IPA☆66Updated 6 months ago
- Various speech datasets made available to the public☆128Updated 8 months ago
- A family of efficient speech models for multilingual phone recognition☆18Updated last week
- TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog☆57Updated last year
- A tiny BERT for low-resource monolingual models☆31Updated 11 months ago
- babyLM WhisBERT code☆20Updated last year
- Repository for SLURP paper☆105Updated 3 years ago
- Speech-MASSIVE is a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSI…☆22Updated last year
- A spoken question answering dataset on SQUAD☆49Updated 4 months ago
- MaSS - Multilingual corpus of Sentence-aligned Spoken utterances☆50Updated 11 months ago
- Official code for Wav2Seq☆96Updated 3 years ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- The Gridspace-Stanford Harper Valley speech dataset. Created in support of CS224S.☆47Updated 4 years ago
- Linguistic processing for Common Voice☆57Updated last year
- CVSS: A Massively Multilingual Speech-to-Speech Translation Corpus☆212Updated 3 years ago
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆76Updated 3 years ago
- Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together☆47Updated 2 months ago
- An easy way to fine-tune Wav2Vec 2.0 for low-resource languages.☆82Updated 2 years ago