Alternatives and similar repositories for open_universal_arabic_asr_leaderboard

Users that are interested in open_universal_arabic_asr_leaderboard are comparing it to the libraries listed below

• abjadai / catt
  The official implementation of CATT Arabic diacritization models.
  ☆58Updated 6 months ago
• mbzuai-nlp / ArTST
  ☆63Updated 6 months ago
• nipponjo / tts_arabic
  🎙️ Arabic TTS models (FastPitch, Mixer-TTS) in the ONNX format — Python package for offline speech synthesis 🚀📦
  ☆36Updated last month
• janhq / WhisperSpeech
  Ichigo Whisper is a compact (22M parameters), open-source speech tokenizer for the Whisper-medium, designed to enhance performance on mul…
  ☆17Updated last year
• ahmedheakl / arazn-llm
  Code-Switched translations with Large Language models
  ☆24Updated last year
• nguyenvulebinh / ViStreamASR
  ViStreamASR - Real-Time Vietnamese Speech Recognition
  ☆52Updated 6 months ago
• mbzuai-oryx / KITAB-Bench
  [ACL 2025 🔥] A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding
  ☆60Updated 7 months ago
• mush42 / mantoq
  Arabic Grapheme-to-Phoneme (G2P) Conversion
  ☆13Updated 10 months ago
• BKHMSI / deep-diacritization
  Official Repository of the Deep Diacritization Paper
  ☆17Updated 5 years ago
• neuphonic / neucodec
  A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.
  ☆143Updated 3 months ago
• almodhfer / Arabic_Diacritization
  Several deep learning models for restoring Arabic diacritics using Pytorch.
  ☆36Updated 3 years ago
• Vyvo-Labs / VyvoTTS
  ☆245Updated last month
• slp-rl / slamkit
  SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming: Training a Speech Language Model on On…
  ☆228Updated 8 months ago
• tarzain / crosstalk
  a simple system for 2-way interruptible voice interactions between human and LLM
  ☆30Updated last year
• herimor / voxtream
  VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency
  ☆181Updated 2 months ago
• EraX-AI / viF5TTS
  EraX Text to Speech base on F5-TTS Base V1
  ☆79Updated 8 months ago
• Vyvo-Labs / SpeechPlus
  SpeechPlus: Small LLM-Based Text-to-Speech Library 🚀
  ☆20Updated 8 months ago
• EndlessReform / smoltts
  Open TTS models, built for streaming on the edge
  ☆44Updated 10 months ago
• 7Xin / DPI-TTS
  ☆13Updated last year
• riotu-lab / aranizer
  Aranizer: A Custom Tokenizer based on SentencePiece and BPE tailored for Arabic Language Modeling
  ☆21Updated last year
• nipponjo / arabic-vocalization
  Arabic deep-learning based diacritization models (Shakkala, Shakkelha) ported to PyTorch
  ☆14Updated 2 years ago
• ARBML / CIDAR
  Instruction dataset for Arabic with 10,000 instruction and output pairs. CIDAR can be used to fine-tune LLMs to follow instructions.
  ☆43Updated 9 months ago
• indonesian-nlp / multilingual-asr
  Multilingual Speech Recognition for Indonesian Languages
  ☆69Updated 3 years ago
• CouncilDataProject / speakerbox
  Speakerbox: Fine-tune Audio Transformers for speaker identification.
  ☆59Updated last year
• ogunlao / yoruba_speech_project
  This repo contains 3 hours of audio speech recordings in Yoruba language collected for research purposes.
  ☆18Updated 5 years ago
• joejoe03 / Egyptian-Text-To-Speech
  ☆37Updated 11 months ago
• apple / pytorch-speech-features
  ☆86Updated last year
• huggingface / open_asr_leaderboard
  ☆158Updated last month
• indri-voice / audiotoken
  Audio tokenization, in the fastest way possible!
  ☆53Updated last year
• ahmedshah1494 / speech_robust_bench
  ☆16Updated 8 months ago