Horizon Team, Xiaomi MiLM Plus

mispeech's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

richermans 

in mispeech/GLAP 5 days ago

Model Weight

1

#2 opened 5 days ago by

kevinpro

richermans 

updated a model 5 days ago

mispeech/dashengtokenizer

Audio-to-Audio • 0.8B • Updated 5 days ago • 69 • 2

richermans 

updated a collection 6 days ago

Dasheng Tokenizer

Collection

Audio Tokenizers for understanding and Generation • 1 item • Updated 6 days ago • 1

richermans 

published a model 6 days ago

mispeech/dashengtokenizer

Audio-to-Audio • 0.8B • Updated 5 days ago • 69 • 2

richermans 

updated 3 models 3 months ago

mispeech/dasheng-1.2B

Audio Classification • 1B • Updated Dec 4, 2025 • 584 • 3

mispeech/dasheng-base

Audio Classification • 85.4M • Updated Dec 4, 2025 • 5.21k • 9

mispeech/dasheng-0.6B

Audio Classification • 0.6B • Updated Dec 4, 2025 • 236 • 2

zhoukz 

updated 2 models 3 months ago

mispeech/midashenglm-7b-0804-bf16

Audio-Text-to-Text • 8B • Updated Nov 11, 2025 • 287

mispeech/midashenglm-7b-1021-bf16

Audio-Text-to-Text • 8B • Updated Nov 11, 2025 • 156 • 2

zhoukz 

updated 6 models 4 months ago

mispeech/midashenglm-7b-1021-w4a16-gptq

Audio-Text-to-Text • 3B • Updated Oct 31, 2025 • 27 • 1

mispeech/midashenglm-7b-1021-fp32

Audio-Text-to-Text • 8B • Updated Oct 31, 2025 • 10

mispeech/midashenglm-7b-1021-fp8

Audio-Text-to-Text • 8B • Updated Oct 31, 2025 • 14 • 1

mispeech/midashenglm-7b-0804-w4a16-gptq

Audio-Text-to-Text • 3B • Updated Oct 31, 2025 • 3

mispeech/midashenglm-7b-0804-fp32

Audio-Text-to-Text • 8B • Updated Oct 31, 2025 • 30k • 77

mispeech/midashenglm-7b-0804-fp8

Audio-Text-to-Text • 8B • Updated Oct 31, 2025 • 6

richermans 

updated a dataset 4 months ago

mispeech/xares_llm_data

Viewer • Updated Oct 29, 2025 • 1.14M • 11k • 2

richermans 

published a dataset 4 months ago

mispeech/xares_llm_data

Viewer • Updated Oct 29, 2025 • 1.14M • 11k • 2

richermans 

updated a collection 4 months ago

CED

Collection

State-of-the-art Efficient Audio classifiers trained on Audioset. • 4 items • Updated Oct 27, 2025