Standard-Intelligence/hertz-dev
first base model for full-duplex conversational audio
PythonApache-2.0
Issues
- 6
Nonsense Responses
#29 opened by MarcoFerreiraPerson - 10
How to run Inference?
#11 opened by SuperMaximus1984 - 1
Inconsistent Output: Clear Results in Notebook vs. Noisy Responses in Inference Client
#34 opened by humblenginr - 1
Use which LLM weights?
#31 opened by SeungdongYoa - 0
RuntimeError: mat1 and mat2 shapes cannot be multiplied (69x64 and 32x4096) in inference_server.py
#33 opened by ahmetkca - 0
The controlability and security of the pure audio modality speech in/out generation
#32 opened by JohnHerry - 7
Inference problem
#9 opened by maciekpoplawski - 1
Tool Use / Function Calling
#30 opened by josiahbryan - 2
Support for macOS & Apple M1-M4
#5 opened by ChristianWeyer - 1
does is support chinese QA
#28 opened by mmlingyu - 0
Better VQ method recommendation
#27 opened by youngsheen - 0
Question about Technical Report
#25 opened by hertz-pj - 1
How many GPUs need to run this code ?
#23 opened by Gpwner - 1
Add a docker container
#14 opened by lu4p - 1
- 1
Thank you for your excellent work. Will you open source the training code and data samples?
#22 opened by SevenMpp - 1
Fauxpen source
#8 opened by flatsiedatsie - 1
Text align?
#20 opened by OnceJune - 2
Undefined external error
#3 opened by SoftologyPro - 1
Integrate with openwebui
#13 opened by lu4p - 0
Better dependency management
#15 opened by lu4p - 1
Questions about bitrate calculation
#2 opened by sphmel - 1
Training
#10 opened by matbee-eth - 3
Pretrain dataset
#1 opened by indiejoseph - 0
- 0
Support for amd rocm
#12 opened by lu4p