Skip to content

Commit

Permalink
[docs] update docs/pretrained.md (#349)
Browse files Browse the repository at this point in the history
  • Loading branch information
JiJiJiang authored Aug 20, 2024
1 parent 655039e commit 8934efe
Show file tree
Hide file tree
Showing 2 changed files with 3 additions and 1 deletion.
2 changes: 2 additions & 0 deletions docs/pretrained.md
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,8 @@ in [the voxconverse recipe](https://github.com/wenet-e2e/wespeaker/tree/master/e

## Model List

The model with suffix **LM** means that it is further fine-tuned using large-margin fine-tuning, which could perform better on long audios, e.g. >3s.

### modelscope

| Datasets | Languages | Checkpoint (pt) | Runtime Model (onnx) |
Expand Down
2 changes: 1 addition & 1 deletion examples/voxceleb/v2/run_wavlm.sh
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ data_type="shard" # shard/raw

config=conf/ecapa_tdnn_WavLM_frozen.yaml
exp_dir=exp/ECAPA_TDNN_GLOB_c512-ASTP-emb192-WavLM_large_frozen_num_frms150-aug0.6-spTrue-saFalse-ArcMargin_intertopk_subcenter-SGD-epoch150
gpus="[0,1,2,3]" #,4,5,6,7]"
gpus="[0,1,2,3,4,5,6,7]"
num_avg=10
checkpoint=

Expand Down

0 comments on commit 8934efe

Please sign in to comment.