Pretrain from scratch 4096 context length on 90B tokens Malaysian text, https://huggingface.co/papers/2401.14680

Mesolitica
company
AI & ML interests
We develop Multimodality, lab from Malaysia
Recent Activity
View all activity
Collections
24
models
258

mesolitica/Malaysian-F5-TTS-v3
Updated

mesolitica/Malaysian-orpheus-3b-0.1-pretrained
Updated

mesolitica/malaysian-parler-tts-tiny-v1
Text2Text Generation
•
Updated
•
23

mesolitica/Malaysian-orpheus-3b-0.1-ft
Text Generation
•
Updated
•
17
•
1

mesolitica/malaysian-parler-tts-mini-v1
Text2Text Generation
•
Updated
•
61

mesolitica/Malaysian-F5-TTS-v2
Updated
•
1

mesolitica/malaysian-vocos-mel-24khz
Updated
•
11

mesolitica/malaysian-whisper-large-v3-turbo-v3
Updated
•
801
•
1

mesolitica/Malaysian-Llama-3.1-8B-Instruct-Marlin
Updated
•
96

mesolitica/Malaysian-Llama-3.2-1B-Instruct-v2
Updated
•
26
datasets
215
mesolitica/AudioSet-Audio-Instructions
Viewer
•
Updated
•
313k
•
16
mesolitica/Speech-Translation-Instructions
Viewer
•
Updated
•
312k
•
36
•
1
mesolitica/Malaysian-Emilia
Updated
•
1.05k
•
2
mesolitica/Classification-Speech-Instructions
Viewer
•
Updated
•
118k
•
38
mesolitica/tts-combine-annotated
Viewer
•
Updated
•
360k
•
53
mesolitica/Malaysian-Speech-Instructions
Viewer
•
Updated
•
469k
•
10
mesolitica/Malaysian-Voice-Conversion
Viewer
•
Updated
•
6.15M
•
399
mesolitica/Malaysian-Speech-Benchmark
Preview
•
Updated
•
214
•
2
mesolitica/Malaysian-Emilia-annotated
Viewer
•
Updated
•
1.24M
•
1.2k
•
1
mesolitica/Malaysian-TTS-Combined
Viewer
•
Updated
•
646k
•
25