Vietnamese speech dataset Collection for any speech-related tasks including but not limited to: speech-to-text & text-to-speech, speech classification, speaker verification, etc. • 31 items • Updated Apr 23 • 22
VoxPopuli v2 Collection A collection of checkpoints from the second VoxPopuli release. • 35 items • Updated Jan 16, 2024 • 6
Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages Paper • 2503.23542 • Published Mar 30 • 10
Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 7 items • Updated May 21 • 145
Model Merging Collection Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12, 2024 • 243
WhisperLah Collection A collection of Whisper-variants for Singapore languages, e.g. English, Mandarin, Bahasa Malaysia, Tamil • 3 items • Updated Nov 27, 2024 • 1
Whisper pruned Collection Pruned / trimmed versions of whisper models with unnecessary languages removed. • 5 items • Updated Jan 30 • 1
distil-large-v3 Collection This collection contains the model repositories for distil-large-v3, which provides support for the most popular Whisper libraries. • 4 items • Updated Mar 21, 2024 • 6
Qwen2 Collection Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated Apr 28 • 366
MaLLaM 🌙 Collection Pretrain from scratch 4096 context length on 90B tokens Malaysian text, https://huggingface.co/papers/2401.14680 • 10 items • Updated 6 days ago • 15
VinaLLaMA Collection Second Generation, Most Powerful Open-Source Vietnamese LLMs. • 8 items • Updated Feb 9, 2024 • 13