This is the experimental family for natively sound understanding
Jan (Homebrew Research) PRO
jan-hq
AI & ML interests
Also at: https://huggingface.co/jan-ai
https://huggingface.co/homebrewltd
Recent Activity
updated
a dataset
18 minutes ago
homebrewltd/viVoice_tokens_v1
updated
a model
41 minutes ago
jan-hq/ichigo-quantizer
updated
a model
6 days ago
cortexso/whispervq
Organizations
Collections
6
spaces
3
models
106
jan-hq/ichigo-quantizer
Updated
jan-hq/llama3.2-3B-base-s-compression
Updated
•
6
jan-hq/llama3.2-1B-base-s-compression
Updated
•
5
jan-hq/llama3.2-1B-s-compression
Updated
•
8
jan-hq/llama3.2-1B-base-s-whispervq-init
Updated
•
15
jan-hq/llama3.2-1B-instruct-fp32-1e4
Text Generation
•
Updated
•
9
jan-hq/llama3.2-1B-instruct-fp32-1e4-cp-1000
Text Generation
•
Updated
•
9
jan-hq/llama3.2-1B-instruct-fp32-1e4-cp-2000
Text Generation
•
Updated
•
13
jan-hq/llama3.2-1B-instruct-fp32-1e4-cp-3000
Text Generation
•
Updated
•
10
jan-hq/Ichigo-llama3.1-s-instruct-v0.4-step-8000
Text Generation
•
Updated
•
16
datasets
126
jan-hq/vivoice
Viewer
•
Updated
•
888k
•
4
jan-hq/alpaca_audio_test
Viewer
•
Updated
•
100
•
45
•
1
jan-hq/instruction-convert-audio-whispervq-llama3.2-compress
Viewer
•
Updated
•
3.71M
•
77
jan-hq/gigaspeech-vie-sub
Viewer
•
Updated
•
52.1k
•
46
jan-hq/instruction-convert-audio-whispervq-llama3.2-dedup
Viewer
•
Updated
•
3.71M
•
37
jan-hq/instruction-convert-audio-whispervq-llama3.2
Viewer
•
Updated
•
3.71M
•
44
jan-hq/mixed-instruction-speech-whispervq-v3-full-phase2-3
Viewer
•
Updated
•
1.98M
•
42
jan-hq/mixed-text-speech-multiturn-noise-data
Viewer
•
Updated
•
2k
•
41
jan-hq/mixed-instruction-speech-multiturn-noise-clean
Viewer
•
Updated
•
165k
•
38
jan-hq/mixed-instruction-speech-multiturn-noise
Viewer
•
Updated
•
165k
•
45