The demo not work, see the following exception #10
Description
(.venv) (base) ✘ 🐍 base xupeng@localhost ~/workspace/git/GPA/scripts/inference ↰ main /Users/xupeng/workspace/git/GPA/.venv/bin/python gpa_inference.py --task stt
--src_audio_path "..
audios/test_app_asr.wav"
--gpa_model_path "${GPA_MODEL_DIR}"
--tokenizer_path "${GPA_MODEL_DIR}/glm-4-voice-tokenizer"
--bicodec_tokenizer_path "${GPA_MODEL_DIR}/BiCodec"
--text_tokenizer_path "${GPA_MODEL_DIR}"
Using device: cpu
Loading tokenizers...
Loading weights: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████| 249/249 [00:00<00:00, 3543.02it/s, Materializing param=layers.15.self_attn_layer_norm.weight]
/Users/xupeng/workspace/git/GPA/.venv/lib/python3.11/site-packages/transformers/modeling_rope_utils.py:927: FutureWarning: rope_config_validation is deprecated and has been removed. Its functionality has been moved to RotaryEmbeddingConfigMixin.validate_rope method. PreTrainedConfig inherits this class, so please call self.validate_rope() instead. Also, make sure to use the new rope_parameters syntax. You can call self.standardize_rope_params() in the meantime.
warnings.warn(
Traceback (most recent call last):
File "/Users/xupeng/workspace/git/GPA/scripts/inference/gpa_inference.py", line 297, in
main()
File "/Users/xupeng/workspace/git/GPA/scripts/inference/gpa_inference.py", line 265, in main
inference = GPAInference(
^^^^^^^^^^^^^
File "/Users/xupeng/workspace/git/GPA/scripts/inference/gpa_inference.py", line 31, in init
self._load_models()
File "/Users/xupeng/workspace/git/GPA/scripts/inference/gpa_inference.py", line 38, in _load_models
self.text_tokenizer = AutoTokenizer.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/xupeng/workspace/git/GPA/.venv/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 702, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/xupeng/workspace/git/GPA/.venv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 1751, in from_pretrained
return cls._from_pretrained(
^^^^^^^^^^^^^^^^^^^^^
File "/Users/xupeng/workspace/git/GPA/.venv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2003, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/xupeng/workspace/git/GPA/.venv/lib/python3.11/site-packages/transformers/models/qwen2/tokenization_qwen2.py", line 89, in init
super().init(
File "/Users/xupeng/workspace/git/GPA/.venv/lib/python3.11/site-packages/transformers/tokenization_utils_tokenizers.py", line 376, in init
self._tokenizer = self._patch_mistral_regex(
^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: transformers.tokenization_utils_tokenizers.TokenizersBackend._patch_mistral_regex() got multiple values for keyword argument 'fix_mistral_regex'
(.venv) (base) ✘ 🐍 base xupeng@localhost ~/workspace/git/GPA/scripts/inference ↰ main