# Reference deploy knobs for Qwen/Qwen3-ForcedAligner-0.6B, the shared forced # aligner for streaming TTS word timestamps. Pass with --forced-aligner-config; # --forced-aligner overrides the model path without editing this file. # # Run as LLM(runner="pooling") with pooling_task="token_classify". Prompt tokens, # chat template and word segmentation are Qwen-specific and live in # qwen3_force_align_processor (not configurable here). forced_aligner: model: Qwen/Qwen3-ForcedAligner-0.6B runner: pooling architecture: Qwen3ASRForcedAlignerForTokenClassification pooling_task: token_classify gpu_memory_utilization: 0.30 dtype: bfloat16 max_model_len: 4096 trust_remote_code: true