D
deepdml
AI & ML interests
ASR & NLP
Recent Activity
new activity 2 days ago
Helsinki-NLP/opus-mt_tiny_cat-spa:RuntimeError: Internal: could not parse ModelProto updated a model 2 days ago
deepdml/whisper-large-v3-distil-dec4-ct2.fr published a model 2 days ago
deepdml/whisper-large-v3-distil-dec4-ct2.frOrganizations
Malay
-
mesolitica/Malaysian-STT-Whisper
Viewer ⢠Updated ⢠14.7M ⢠340 ⢠4 -
malaysia-ai/iban-whisper-format
Preview ⢠Updated ⢠5 -
mesolitica/pseudolabel-malaysian-youtube-whisper-large-v3
Preview ⢠Updated ⢠54 ⢠3 -
mesolitica/pseudolabel-malaysian-youtube-whisper-large-v3-timestamp
Viewer ⢠Updated ⢠3.09M ⢠1.59k
Tamil
Tamil refers to a Dravidian language, an ethnic group, and a rich culture originating from South India, known as one of the world's oldest living clas
TTS
Text-to-speech
OCR
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text ⢠1.0B ⢠Updated ⢠6.76k ⢠1.59k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text ⢠4B ⢠Updated ⢠460k ⢠498 -
Qwen/Qwen3-VL-8B-Instruct
Image-Text-to-Text ⢠9B ⢠Updated ⢠3.97M ⢠⢠864 -
Qwen/Qwen3-VL-8B-Instruct-FP8
Image-Text-to-Text ⢠9B ⢠Updated ⢠295k ⢠67
South Africa
Afrikaans and Zulu
Khmer
Khmer refers to the dominant ethnic group and official language of Cambodia.
Tamazight
https://huggingface.co/Tamazight-NLP
Diarization
-
nvidia/multitalker-parakeet-streaming-0.6b-v1
Automatic Speech Recognition ⢠Updated ⢠717 ⢠98 - Running33
Speaker Diarization
š„33Speaker diarization, speake segmentation,
-
pyannote/speaker-diarization-community-1
Automatic Speech Recognition ⢠Updated ⢠2.32M ⢠291 - Sleeping
PrecisionVoice
šTranscribe audio with speaker identification
Darija
https://huggingface.co/blog/atlasia/darija-chatbot-arena
-
atlasia/Moroccan-Darija-Wiki-Audio-Dataset
Viewer ⢠Updated ⢠492 ⢠106 ⢠14 -
atlasia/DODa-audio-dataset
Viewer ⢠Updated ⢠12.7k ⢠556 ⢠17 -
MBZUAI-Paris/Darija-SFT-Mixture
Viewer ⢠Updated ⢠458k ⢠91 ⢠18 - Paused14
Darija Chatbot Arena
š14Generate images from text descriptions
Quran ASR
South Africa
Afrikaans and Zulu
Malay
-
mesolitica/Malaysian-STT-Whisper
Viewer ⢠Updated ⢠14.7M ⢠340 ⢠4 -
malaysia-ai/iban-whisper-format
Preview ⢠Updated ⢠5 -
mesolitica/pseudolabel-malaysian-youtube-whisper-large-v3
Preview ⢠Updated ⢠54 ⢠3 -
mesolitica/pseudolabel-malaysian-youtube-whisper-large-v3-timestamp
Viewer ⢠Updated ⢠3.09M ⢠1.59k
Khmer
Khmer refers to the dominant ethnic group and official language of Cambodia.
Tamil
Tamil refers to a Dravidian language, an ethnic group, and a rich culture originating from South India, known as one of the world's oldest living clas
Tamazight
https://huggingface.co/Tamazight-NLP
TTS
Text-to-speech
Diarization
-
nvidia/multitalker-parakeet-streaming-0.6b-v1
Automatic Speech Recognition ⢠Updated ⢠717 ⢠98 - Running33
Speaker Diarization
š„33Speaker diarization, speake segmentation,
-
pyannote/speaker-diarization-community-1
Automatic Speech Recognition ⢠Updated ⢠2.32M ⢠291 - Sleeping
PrecisionVoice
šTranscribe audio with speaker identification
OCR
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text ⢠1.0B ⢠Updated ⢠6.76k ⢠1.59k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text ⢠4B ⢠Updated ⢠460k ⢠498 -
Qwen/Qwen3-VL-8B-Instruct
Image-Text-to-Text ⢠9B ⢠Updated ⢠3.97M ⢠⢠864 -
Qwen/Qwen3-VL-8B-Instruct-FP8
Image-Text-to-Text ⢠9B ⢠Updated ⢠295k ⢠67
Darija
https://huggingface.co/blog/atlasia/darija-chatbot-arena
-
atlasia/Moroccan-Darija-Wiki-Audio-Dataset
Viewer ⢠Updated ⢠492 ⢠106 ⢠14 -
atlasia/DODa-audio-dataset
Viewer ⢠Updated ⢠12.7k ⢠556 ⢠17 -
MBZUAI-Paris/Darija-SFT-Mixture
Viewer ⢠Updated ⢠458k ⢠91 ⢠18 - Paused14
Darija Chatbot Arena
š14Generate images from text descriptions