Skip to content

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

install requirements automatically

游雁1df10311c4e6
diff --git a/funasr/tokenizer/hf_tokenizer.py b/funasr/tokenizer/hf_tokenizer.py
index 81f553d79..b6043e95b 100644
--- a/funasr/tokenizer/hf_tokenizer.py
+++ b/funasr/tokenizer/hf_tokenizer.py
@@ -1,15 +1,15 @@
-try:
- from transformers import AutoTokenizer
-except:
- # print("If you want to use hugging, please `pip install -U transformers`")
- pass
+
from funasr.register import tables
@tables.register("tokenizer_classes", "HuggingfaceTokenizer")
def HuggingfaceTokenizer(init_param_path, **kwargs):
-
+ try:
+ from transformers import AutoTokenizer
+ except:
+ # print("If you want to use hugging, please `pip install -U transformers`")
+ pass
tokenizer = AutoTokenizer.from_pretrained(init_param_path)
return tokenizer
diff --git a/funasr/tokenizer/whisper_tokenizer.py b/funasr/tokenizer/whisper_tokenizer.py
index 3fb5b645c..6684f2598 100644
--- a/funasr/tokenizer/whisper_tokenizer.py
+++ b/funasr/tokenizer/whisper_tokenizer.py
@@ -1,14 +1,14 @@
-try:
- from whisper.tokenizer import get_tokenizer
-except:
- print("Notice: If you want to use whisper, please `pip install -U openai-whisper`")
from funasr.register import tables
@tables.register("tokenizer_classes", "WhisperTokenizer")
def WhisperTokenizer(**kwargs):
-
+ try:
+ from whisper.tokenizer import get_tokenizer
+ except:
+ print("Notice: If you want to use whisper, please `pip install -U openai-whisper`")
+
language = kwargs.get("language", None)
task = kwargs.get("task", "transcribe")
is_multilingual = kwargs.get("is_multilingual", True)