From 7ac54b3c97491ee9ac8a8ebbb7033240864f805a Mon Sep 17 00:00:00 2001
From: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Date: 星期二, 18 七月 2023 19:26:01 +0800
Subject: [PATCH] add lora finetune code
---
funasr/bin/build_trainer.py | 8 ++++++--
1 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/funasr/bin/build_trainer.py b/funasr/bin/build_trainer.py
index df921fa..bd30a83 100644
--- a/funasr/bin/build_trainer.py
+++ b/funasr/bin/build_trainer.py
@@ -23,6 +23,8 @@
from funasr.tasks.asr import ASRTask as ASRTask
elif mode == "paraformer":
from funasr.tasks.asr import ASRTaskParaformer as ASRTask
+ 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
elif mode == "uniasr":
@@ -83,6 +85,7 @@
finetune_configs = yaml.safe_load(f)
# set data_types
if dataset_type == "large":
+ # 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)
@@ -132,8 +135,7 @@
if args.dataset_type == "small":
args.batch_bins = batch_bins
elif args.dataset_type == "large":
- # args.dataset_conf["batch_conf"]["batch_size"] = batch_bins
- pass
+ args.dataset_conf["batch_conf"]["batch_size"] = batch_bins
else:
raise ValueError(f"Not supported dataset_type={args.dataset_type}")
if args.normalize in ["null", "none", "None"]:
@@ -142,6 +144,8 @@
args.patience = None
args.local_rank = local_rank
args.distributed = distributed
+ for key, value in kwargs.items():
+ args.key = value
ASRTask.finetune_args = args
return ASRTask
--
Gitblit v1.9.1