From fd6d78ced9686dee51f2ac41a8cfb5e50dcb3b37 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 08 八月 2023 18:59:13 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/bin/build_trainer.py | 20 ++++++++++++++++----
1 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/funasr/bin/build_trainer.py b/funasr/bin/build_trainer.py
index 3873239..e7f28ed 100644
--- a/funasr/bin/build_trainer.py
+++ b/funasr/bin/build_trainer.py
@@ -2,7 +2,6 @@
import yaml
-
def update_dct(fin_configs, root):
if root == {}:
return {}
@@ -23,7 +22,7 @@
from funasr.tasks.asr import ASRTask as ASRTask
elif mode == "paraformer":
from funasr.tasks.asr import ASRTaskParaformer as ASRTask
- elif mode == "paraformer_online":
+ elif mode == "paraformer_streaming":
from funasr.tasks.asr import ASRTaskParaformer as ASRTask
elif mode == "paraformer_vad_punc":
from funasr.tasks.asr import ASRTaskParaformer as ASRTask
@@ -55,7 +54,7 @@
scheduler_conf=None,
specaug=None,
specaug_conf=None,
- param_dict=None,
+ mate_params=None,
**kwargs):
mode = modelscope_dict['mode']
args, ASRTask = parse_args(mode=mode)
@@ -85,11 +84,21 @@
finetune_configs = yaml.safe_load(f)
# set data_types
if dataset_type == "large":
- finetune_configs["dataset_conf"]["data_types"] = "sound,text"
+ # finetune_configs["dataset_conf"]["data_types"] = "sound,text"
+ if 'data_types' not in finetune_configs['dataset_conf']:
+ finetune_configs["dataset_conf"]["data_types"] = "sound,text"
finetune_configs = update_dct(configs, finetune_configs)
for key, value in finetune_configs.items():
if hasattr(args, key):
setattr(args, key, value)
+ if mate_params is not None:
+ for key, value in mate_params.items():
+ if hasattr(args, key):
+ setattr(args, key, value)
+ if mate_params is not None and "lora_params" in mate_params:
+ lora_params = mate_params['lora_params']
+ configs['encoder_conf'].update(lora_params)
+ configs['decoder_conf'].update(lora_params)
# prepare data
args.dataset_type = dataset_type
@@ -104,6 +113,9 @@
else:
raise ValueError(f"Not supported dataset_type={args.dataset_type}")
args.init_param = [init_param]
+ if mate_params is not None and "init_param" in mate_params:
+ if len(mate_params["init_param"]) != 0:
+ args.init_param = mate_params["init_param"]
args.cmvn_file = cmvn_file
if os.path.exists(seg_dict_file):
args.seg_dict_file = seg_dict_file
--
Gitblit v1.9.1