Unified_Audio_Schema
tencent/Unified_Audio_Schema
- kind
- original
- quant
- bf16 (16-bit)
- family
- misc
- modality
- audio-text-to-text
- root model
- —
- provider
- tencent
- license
- —
- language
- —
- context
- —
- library
- —
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 20
- likes
- 11
- created
- —
- last modified
- 2026-04-16T07:41:15+00:00 (2026)
- huggingface
- https://huggingface.co/tencent/Unified_Audio_Schema
- tags
- safetensorsuas_audioaudiospeechsoundmusicaudio-understandingASRaudio-captioningTTSaudio-language-modelaudio-llmspeech-to-texttext-to-speechmultimodalaudio-text-to-textcustom_codeenzharxiv:2604.12506base_model:Qwen/Qwen2.5-7Bbase_model:finetune:Qwen/Qwen2.5-7Blicense:otherregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.