Am begginer in python Select this topic as project in my final year and Using

Hi <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="

Can you please help to run this project code about visual_speech_recognition_for_multiple_languages HOT 2 CLOSED

nishachalingal commented on June 22, 2024

Can you please help to run this project code

from visual_speech_recognition_for_multiple_languages.

Comments (2)

mpc001 commented on June 22, 2024

Hi @nishachalingal, you can download and extract a pre-trained model to the directory ./benchmarks/${dataset}/models, which is the default setting. Alternatively, you can put the model to a directory other than that one. An extra step for the latter option is that you need to correspondingly change the model_path and model_conf at the configuration file in configs folder.

from visual_speech_recognition_for_multiple_languages.

M1ndBlast commented on June 22, 2024

Hey there.

I already installed requirements, model and language model.

I wonder which video format I must have. I'm using mp4 files and I get next error

(autoavsr) PS D:\Visual_Speech_Recognition_for_Multiple_Languages> python .\infer.py config_filename=.\configs\LRS3_V_WER19.1.ini data_filename=.\Grabacion.mp4 detector=mediapipe
Error executing job with overrides: ['config_filename=.\\configs\\LRS3_V_WER19.1.ini', 'data_filename=.\\Grabacion.mp4', 'detector=mediapipe']
Traceback (most recent call last):
  File ".\infer.py", line 15, in main
    output = InferencePipeline(cfg.config_filename, device=device, detector=cfg.detector, face_track=True)(cfg.data_filename, cfg.landmarks_filename)
  File "D:\Visual_Speech_Recognition_for_Multiple_Languages\pipelines\pipeline.py", line 45, in __init__
    self.model = AVSR(modality, model_path, model_conf, rnnlm, rnnlm_conf, penalty, ctc_weight, lm_weight, beam_size, device)
  File "D:\Visual_Speech_Recognition_for_Multiple_Languages\pipelines\model.py", line 43, in __init__
    self.token_list = ['<blank>'] + [word.split()[0] for word in open(file_path).read().splitlines()] + ['<eos>']
  File "C:\Users\peduz\miniconda3\envs\autoavsr\lib\encodings\cp1252.py", line 23, in decode
    return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 4416: character maps to <undefined>

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

Can u help me?

from visual_speech_recognition_for_multiple_languages.

Recommend Projects