Namespace(asr_type='llm', model_dir='/root/tts_asr/FireRedASR/examples/pretrained_models/FireRedASR-LLM-L', wav_path='wav/cmd1740120703406.wav', wav_paths=None, wav_dir=None, wav_scp=None, output='out/llm-l-asr.txt', use_gpu=1, batch_size=1, beam_size=3, decode_max_len=0, nbest=1, softmax_smoothing=1.0, aed_length_penalty=0.0, eos_penalty=1.0, decode_min_len=0, repetition_penalty=3.0, llm_length_penalty=1.0, temperature=1.0)
#wavs=1
model args: Namespace(input_length_max=30.0, input_length_min=0.1, output_length_max=150, output_length_min=1, freeze_encoder=0, encoder_downsample_rate=2, freeze_llm=0, use_flash_attn=0, use_lora=1, unk='', use_fp16=0, encoder_path='/root/tts_asr/FireRedASR/examples/pretrained_models/FireRedASR-LLM-L/asr_encoder.pth.tar', llm_dir='/root/tts_asr/FireRedASR/examples/pretrained_models/FireRedASR-LLM-L/Qwen2-7B-Instruct')
Traceback (most recent call last):
File "/root/tts_asr/FireRedASR/fireredasr/speech2text.py", line 105, in
main(args)
File "/root/tts_asr/FireRedASR/fireredasr/speech2text.py", line 43, in main
model = FireRedAsr.from_pretrained(args.asr_type, args.model_dir)
File "/root/tts_asr/FireRedASR/fireredasr/models/fireredasr.py", line 31, in from_pretrained
model, tokenizer = load_firered_llm_model_and_tokenizer(
File "/root/tts_asr/FireRedASR/fireredasr/models/fireredasr.py", line 122, in load_firered_llm_model_and_tokenizer
model = FireRedAsrLlm.from_args(package["args"])
File "/root/tts_asr/FireRedASR/fireredasr/models/fireredasr_llm.py", line 33, in from_args
encoder, encoder_dim = cls.load_encoder(args.encoder_path)
File "/root/tts_asr/FireRedASR/fireredasr/models/fireredasr_llm.py", line 23, in load_encoder
model.load_state_dict(package["model_state_dict"], strict=False)
KeyError: 'model_state_dict'
FireRedTeam
