Hugging Face's logo

FunAudioLLM
/
Fun-ASR-Nano-2512-hf

Automatic Speech Recognition
Transformers
Safetensors
fun_asr_nano
text-generation
speech-recognition
asr
end-to-end
multilingual
streaming
arxiv:2407.04051
Model card Files
xet
 Community
3

Refresh checkpoint for shared Whisper component layout

#2
by langgz - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+17
-19
langgz
 FunAudioLLM org

Re-converted from source revision 272c57b with Transformers PR #46180 after the shared audio-component refactor. Local validation: 1540 tensors, zero missing/unexpected/mismatched keys; exact Chinese, English, and batch H100 outputs; PR RUN_SLOW integration tests 3 passed.
Refresh checkpoint for shared Whisper component layout6367f428
 Regenerate checkpoint for current Transformers layoutc49669b7
langgz
 FunAudioLLM org

Validated and ready to merge.
langgz changed pull request status to open
langgz
 FunAudioLLM org

Merging verified checkpoint c49669b7.
langgz changed pull request status to merged

Sign up or log in to comment