ARBML / whisperarLinks
☆42Updated 2 years ago
Alternatives and similar repositories for whisperar
Users that are interested in whisperar are comparing it to the libraries listed below
Sorting:
- Several deep learning models for restoring Arabic diacritics using Pytorch.☆35Updated 3 years ago
- ☆56Updated 2 months ago
- This is a diacritization model for Arabic language. This model was built/trained using the Tashkeela: the Arabic diacritization corpus on…☆44Updated 2 years ago
- The official implementation of CATT Arabic diacritization models.☆54Updated 2 months ago
- Benchmark Arabic text diacritization dataset☆76Updated 6 years ago
- A Docker image for a relatively light-weight full Arabic speech synthesis system☆32Updated 4 years ago
- Official Repository of the Deep Diacritization Paper☆16Updated 4 years ago
- Text to Speech for Indic languages☆51Updated 3 years ago
- Arabic cleaning, normalization and segmentation library.☆72Updated 2 years ago
- The first Dialectal Arabic Code Switching - DACS corpus from broadcast speech. Annotated at the token-level, considering both the linguis…☆15Updated 3 years ago
- Arabic deep-learning based diacritization models (Shakkala, Shakkelha) ported to PyTorch☆14Updated 2 years ago
- Context-Sensitive Neural Spelling Checker☆20Updated last year
- Convert Arabic diacritised text to a sequence of phonemes and create a pronunciation dictionary from them for alignment using HTK☆61Updated 8 years ago
- Instruction dataset for Arabic with 10,000 instruction and output pairs. CIDAR can be used to fine-tune LLMs to follow instructions.☆41Updated 6 months ago
- Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2☆92Updated last month
- Python intefrace for evaluation on chatgpt models☆19Updated last year
- Repository containing experimentation platform on how to train, infer on wav2vec2 models.☆87Updated 3 years ago
- ☆43Updated 2 years ago
- HF's ML for Audio study group☆197Updated 2 years ago
- TURJUMAN, a neural toolkit for translating from 20 languages into Modern Standard Arabic (MSA).☆57Updated 2 years ago
- A Python implementation of Farasa toolkit☆136Updated 3 weeks ago
- Aranizer: A Custom Tokenizer based on SentencePiece and BPE tailored for Arabic Language Modeling☆20Updated last year
- A framework for Arabic spelling correction using different seq2seq model architectures such as transformers and RNNs☆22Updated last year
- End to end Arabic TTS system based on tacotron☆121Updated last year
- ☆47Updated 2 years ago
- Code and models for "The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models". EACL 2021, WANLP.☆54Updated last year
- A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models☆31Updated 4 years ago
- This will hold the data pipeline to convert raw audio data to speech which will act as input dataset for speech-to-text pipeline☆32Updated 2 years ago
- Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode☆111Updated 3 years ago
- Traditional ASR (Signal & Cepstral Analysis, DTW, HMM) & DNNs (Custom Models + DeepSpeech) on Indian Accent Speech☆92Updated last year