游雁 0cbf26e0c7 fix: increase inference_batch_size from 1 to 32 in aishell recipes ...

The conformer, transformer, branchformer, and e_branchformer recipes
had inference_batch_size=1 which made GPU decoding extremely slow
(processing one utterance at a time). Changed to 32 to match the
paraformer recipe and utilize GPU parallelism during inference.

2026-05-23 21:21:02 +08:00

..

branchformer

fix: increase inference_batch_size from 1 to 32 in aishell recipes

2026-05-23 21:21:02 +08:00

conformer

fix: increase inference_batch_size from 1 to 32 in aishell recipes

2026-05-23 21:21:02 +08:00

e_branchformer

fix: increase inference_batch_size from 1 to 32 in aishell recipes

2026-05-23 21:21:02 +08:00

e_paraformer

Support eparaformer model on aishell1 recipe (#2327)

2024-12-21 17:13:46 +08:00

paraformer

Dev gzf deepspeed (#1750)

2024-05-23 09:57:14 +08:00

transformer

fix: increase inference_batch_size from 1 to 32 in aishell recipes

2026-05-23 21:21:02 +08:00