Hugging Face's logo

aufklarer
/
Qwen3-ForcedAligner-0.6B-CoreML-FP16

Audio Classification
Core ML
forced-alignment
speech
qwen3
timestamps
neural-engine
Model card Files
xet
 Community
Qwen3-ForcedAligner-0.6B-CoreML-FP16 / audio_encoder.mlmodelc /weights

Commit History

CoreML forced aligner — T=768, inline fp16 embedding gather, stride-aware MLMultiArray access, finite -1e4 causal mask
04ca8c2
verified

aufklarer commited on