Tamazight

AI & ML interests

• See Also: huggingface.co/Tachelhit 🤗

Tamazight 's collections 9

High-fidelity text-to-speech models for Tamazight. Advancing speech synthesis for the Amazigh language through open-source AI and open science.

Running on Zero

Agents

21

Higgs Audio v3 TTS (100 languages)

🍋

21

Zero-shot TTS & voice cloning with Higgs Audio v3 (4B)
multimodalart/higgs-audio-v3-tts-4b-transformers

Text-to-Speech • 5B • Updated Jun 5 • 38.7k • 23
k2-fsa/OmniVoice

Text-to-Speech • 0.6B • Updated Jul 3 • 1.8M • 1.57k
bosonai/higgs-tts-3-4b

Text-to-Speech • 5B • Updated Sep 4 • 120k • 813

Tifinagh-OCR-Datasets

Empowering Tifinagh AI. Open-source OCR data: single-line for Encoder/Decoder pipelines, and full-page layouts for end-to-end models.

Tamazight/Tifinagh-OCR-200k

Viewer • Updated Jun 29 • 200k • 1.59k • 3
Tamazight/Tifinagh-OCR-39K

Viewer • Updated May 17 • 39.1k • 1.51k • 5
Tamazight/Tifinagh-OCR-Augmented-10K

Viewer • Updated May 14 • 10k • 85 • 4
Tamazight/Tifinagh-OCR-Pages-11K

Viewer • Updated May 14 • 11.2k • 34 • 2

Tamazight MT Models

High-performance neural machine translation models for the Tamazight language. Optimized for multilingual open-source applications.

facebook/nllb-200-distilled-600M

Translation • Updated Feb 14, 2024 • 847k • 995
facebook/nllb-200-distilled-1.3B

Translation • Updated Feb 11, 2023 • 480k • 192

Tamazight-Parallel

High-quality parallel datasets and multilingual corpora for Tamazight. Essential for training robust translation and cross-lingual AI models.

Tamazight/Numbers

Viewer • Updated Jan 24, 2025 • 1M • 25 • 6
Tamazight-NLP/TAWNZA_TIFINAGH_ARABIC_DATASET

Viewer • Updated Apr 20 • 132k • 38 • 8
abdelhaqueidali/Amazigh-English-Tatoeba-Extended

Preview • Updated Jun 11 • 34 • 1

Dialogues

Tamazight/Cinema-dialogues-QA

Viewer • Updated Apr 1, 2025 • 50 • 34 • 7
Tamazight/Football-dialogues-QA

Viewer • Updated Nov 17, 2024 • 22 • 15 • 4

Tifinagh OCR Models

Empowering the Tamazight language in the AI era. Open-source Tifinagh OCR models designed for accurate document digitization.

Tamazight/TrOCR-Tifinagh-Small

Image-Text-to-Text • 28.8M • Updated May 14 • 14 • 2
Tamazight/Tifinagh-Nougat-Small

Image-Text-to-Text • 0.2B • Updated May 14 • 16 • 3

Text Datasets

Foundational Tamazight text corpora for NLP. Curated datasets optimized for pre-training and fine-tuning language models.

omarkamali/wikipedia-monthly

Updated about 4 hours ago • 10.9k • 84
Tamazight/Randomly

Viewer • Updated Nov 11, 2024 • 2k • 29 • 6

Tamazight Dictionaries

Comprehensive Tamazight lexical resources. Open-source dictionaries and glossaries for NLP, translation, and linguistic research.

Tamazight/Tamazight-Verbs

Viewer • Updated Mar 1, 2025 • 4.48k • 32 • 6
Tamazight/Countries_en_zgh

Viewer • Updated Nov 3, 2024 • 210 • 21 • 6
abdelhaqueidali/English-Tamazight-Dictionnary-2007

Viewer • Updated Jun 17 • 5.53k • 32
abdelhaqueidali/ircam-dglai-dataset

Viewer • Updated Jun 11 • 17.5k • 9 • 1

Audio Datasets

Curated audio and speech datasets for Tamazight. Essential resources for training automatic speech recognition (ASR) and text-to-speech (TTS) models.

fsicoli/common_voice_19_0

Updated Sep 19, 2024 • 3.35k • 9
Tamazight-NLP/TOSD

Viewer • Updated Apr 21 • 1.8k • 63 • 3

Tamazight TTS Models

High-fidelity text-to-speech models for Tamazight. Advancing speech synthesis for the Amazigh language through open-source AI and open science.

Running on Zero

Agents

21

Higgs Audio v3 TTS (100 languages)

🍋

21

Zero-shot TTS & voice cloning with Higgs Audio v3 (4B)
multimodalart/higgs-audio-v3-tts-4b-transformers

Text-to-Speech • 5B • Updated Jun 5 • 38.7k • 23
k2-fsa/OmniVoice

Text-to-Speech • 0.6B • Updated Jul 3 • 1.8M • 1.57k
bosonai/higgs-tts-3-4b

Text-to-Speech • 5B • Updated Sep 4 • 120k • 813

Tifinagh OCR Models

Empowering the Tamazight language in the AI era. Open-source Tifinagh OCR models designed for accurate document digitization.

Tamazight/TrOCR-Tifinagh-Small

Image-Text-to-Text • 28.8M • Updated May 14 • 14 • 2
Tamazight/Tifinagh-Nougat-Small

Image-Text-to-Text • 0.2B • Updated May 14 • 16 • 3

Tifinagh-OCR-Datasets

Empowering Tifinagh AI. Open-source OCR data: single-line for Encoder/Decoder pipelines, and full-page layouts for end-to-end models.

Tamazight/Tifinagh-OCR-200k

Viewer • Updated Jun 29 • 200k • 1.59k • 3
Tamazight/Tifinagh-OCR-39K

Viewer • Updated May 17 • 39.1k • 1.51k • 5
Tamazight/Tifinagh-OCR-Augmented-10K

Viewer • Updated May 14 • 10k • 85 • 4
Tamazight/Tifinagh-OCR-Pages-11K

Viewer • Updated May 14 • 11.2k • 34 • 2

Text Datasets

Foundational Tamazight text corpora for NLP. Curated datasets optimized for pre-training and fine-tuning language models.

omarkamali/wikipedia-monthly

Updated about 4 hours ago • 10.9k • 84
Tamazight/Randomly

Viewer • Updated Nov 11, 2024 • 2k • 29 • 6

Tamazight MT Models

High-performance neural machine translation models for the Tamazight language. Optimized for multilingual open-source applications.

facebook/nllb-200-distilled-600M

Translation • Updated Feb 14, 2024 • 847k • 995
facebook/nllb-200-distilled-1.3B

Translation • Updated Feb 11, 2023 • 480k • 192

Tamazight Dictionaries

Comprehensive Tamazight lexical resources. Open-source dictionaries and glossaries for NLP, translation, and linguistic research.

Tamazight/Tamazight-Verbs

Viewer • Updated Mar 1, 2025 • 4.48k • 32 • 6
Tamazight/Countries_en_zgh

Viewer • Updated Nov 3, 2024 • 210 • 21 • 6
abdelhaqueidali/English-Tamazight-Dictionnary-2007

Viewer • Updated Jun 17 • 5.53k • 32
abdelhaqueidali/ircam-dglai-dataset

Viewer • Updated Jun 11 • 17.5k • 9 • 1

Tamazight-Parallel

High-quality parallel datasets and multilingual corpora for Tamazight. Essential for training robust translation and cross-lingual AI models.

Tamazight/Numbers

Viewer • Updated Jan 24, 2025 • 1M • 25 • 6
Tamazight-NLP/TAWNZA_TIFINAGH_ARABIC_DATASET

Viewer • Updated Apr 20 • 132k • 38 • 8
abdelhaqueidali/Amazigh-English-Tatoeba-Extended

Preview • Updated Jun 11 • 34 • 1

Audio Datasets

Curated audio and speech datasets for Tamazight. Essential resources for training automatic speech recognition (ASR) and text-to-speech (TTS) models.

fsicoli/common_voice_19_0

Updated Sep 19, 2024 • 3.35k • 9
Tamazight-NLP/TOSD

Viewer • Updated Apr 21 • 1.8k • 63 • 3

Dialogues

Tamazight/Cinema-dialogues-QA

Viewer • Updated Apr 1, 2025 • 50 • 34 • 7
Tamazight/Football-dialogues-QA

Viewer • Updated Nov 17, 2024 • 22 • 15 • 4

AI & ML interests

Team members 1

Tamazight 's collections 9

Higgs Audio v3 TTS (100 languages)

Higgs Audio v3 TTS (100 languages)