Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

update

游雁3e99d0e8269c
diff --git a/examples/industrial_data_pretraining/fun_asr_nano/model.py b/examples/industrial_data_pretraining/fun_asr_nano/model.py
index 308740083..c2830e815 100644
--- a/examples/industrial_data_pretraining/fun_asr_nano/model.py
+++ b/examples/industrial_data_pretraining/fun_asr_nano/model.py
@@ -15,7 +15,7 @@ from funasr.register import tables
from funasr.train_utils.device_funcs import force_gatherable, to_device
from funasr.utils.datadir_writer import DatadirWriter
from funasr.utils.load_utils import extract_fbank, load_audio_text_image_video
-from transformers import AutoConfig, AutoModelForCausalLM
+
from ctc import CTC
from tools.utils import forced_align
@@ -72,6 +72,7 @@ class FunASRNano(nn.Module):
self.llm = None
init_param_path = llm_conf.get("init_param_path", None)
llm_dim = None
+ from transformers import AutoConfig, AutoModelForCausalLM
llm_load_kwargs = llm_conf.get("load_kwargs", {})
config = AutoConfig.from_pretrained(init_param_path)