mirror of https://github.com/modelscope/FunASR.git synced 2026-10-12 02:19:18 +00:00

Files

T

History

游雁 ac7e3ee8a2 fix: revert inference_batch_size for non-Paraformer models

Conformer, Transformer, and Branchformer models raise
NotImplementedError for batch decoding. Only Paraformer and
e_paraformer support batch_size>1 for inference. Revert the
non-Paraformer recipes back to batch_size=1.

2026-05-24 01:54:05 +08:00

conf

Dev gzf new (#1574 )

2024-04-02 10:33:27 +08:00

local

update

2024-02-20 14:35:51 +08:00

demo_infer.sh

Dev gzf (#1379 )

2024-02-22 12:07:30 +08:00

demo_train_or_finetune.sh

Dev gzf (#1379 )

2024-02-22 12:07:30 +08:00

README.md

Dev gzf new (#1574 )

2024-04-02 10:33:27 +08:00

run.sh

fix: revert inference_batch_size for non-Paraformer models

2026-05-24 01:54:05 +08:00

utils

update

2024-02-20 14:35:51 +08:00

README.md

E-Branchformer Result

Training Config

Feature info: using raw speech, extracting 80 dims fbank online, global cmvn, speed perturb(0.9, 1.0, 1.1), specaugment
Train info: lr 0.001, batch_size 10000, 4 gpu(Tesla V100), acc_grad 1, 180 epochs
Train config: conf/train_asr_e_branchformer.yaml
LM config: LM was not used

Results (CER)

testset	CER(%)
dev	4.10
test	4.52