search

huggingface / distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
MIT License
3.33k stars 238 forks source link

RuntimeError: Error(s) in loading state_dict for WhisperForConditionalGeneration. #64

Open Eskaggg opened 6 months ago

Eskaggg commented 6 months ago

Hi @sanchit-gandhi I have followed the instruction to do the training but in the training section I get the below error. How to fix? Traceback (most recent call last): File "/home/codelex/Documents/lawly/linear_regression/distil-whisper/training/Distil-whisper-mn/create_student_model.py", line 206, in init_student_model_from_teacher( File "/home/codelex/Documents/lawly/linear_regression/distil-whisper/training/Distil-whisper-mn/create_student_model.py", line 134, in init_student_model_from_teacher raise RuntimeError( RuntimeError: Error(s) in loading state_dict for WhisperForConditionalGeneration. Missing key(s) in state_dict: ['model.encoder.layers.4.self_attn.k_proj.weight', 'model.encoder.layers.4.self_attn.v_proj.weight', 'model.encoder.layers.4.self_attn.v_proj.bias', 'model.encoder.layers.4.self_attn.q_proj.weight', 'model.encoder.layers.4.self_attn.q_proj.bias', 'model.encoder.layers.4.self_attn.out_proj.weight', 'model.encoder.layers.4.self_attn.out_proj.bias', 'model.encoder.layers.4.self_attn_layer_norm.weight', 'model.encoder.layers.4.self_attn_layer_norm.bias', 'model.encoder.layers.4.fc1.weight', 'model.encoder.layers.4.fc1.bias', 'model.encoder.layers.4.fc2.weight', 'model.encoder.layers.4.fc2.bias', 'model.encoder.layers.4.final_layer_norm.weight', 'model.encoder.layers.4.final_layer_norm.bias', 'model.encoder.layers.5.self_attn.k_proj.weight', 'model.encoder.layers.5.self_attn.v_proj.weight', 'model.encoder.layers.5.self_attn.v_proj.bias', 'model.encoder.layers.5.self_attn.q_proj.weight', 'model.encoder.layers.5.self_attn.q_proj.bias', 'model.encoder.layers.5.self_attn.out_proj.weight', 'model.encoder.layers.5.self_attn.out_proj.bias', 'model.encoder.layers.5.self_attn_layer_norm.weight', 'model.encoder.layers.5.self_attn_layer_norm.bias', 'model.encoder.layers.5.fc1.weight', 'model.encoder.layers.5.fc1.bias', 'model.encoder.layers.5.fc2.weight', 'model.encoder.layers.5.fc2.bias', 'model.encoder.layers.5.final_layer_norm.weight', 'model.encoder.layers.5.final_layer_norm.bias', 'model.encoder.layers.6.self_attn.k_proj.weight', 'model.encoder.layers.6.self_attn.v_proj.weight', 'model.encoder.layers.6.self_attn.v_proj.bias', 'model.encoder.layers.6.self_attn.q_proj.weight', 'model.encoder.layers.6.self_attn.q_proj.bias', 'model.encoder.layers.6.self_attn.out_proj.weight', 'model.encoder.layers.6.self_attn.out_proj.bias', 'model.encoder.layers.6.self_attn_layer_norm.weight', 'model.encoder.layers.6.self_attn_layer_norm.bias', 'model.encoder.layers.6.fc1.weight', 'model.encoder.layers.6.fc1.bias', 'model.encoder.layers.6.fc2.weight', 'model.encoder.layers.6.fc2.bias', 'model.encoder.layers.6.final_layer_norm.weight', 'model.encoder.layers.6.final_layer_norm.bias', 'model.encoder.layers.7.self_attn.k_proj.weight', 'model.encoder.layers.7.self_attn.v_proj.weight', 'model.encoder.layers.7.self_attn.v_proj.bias', 'model.encoder.layers.7.self_attn.q_proj.weight', 'model.encoder.layers.7.self_attn.q_proj.bias', 'model.encoder.layers.7.self_attn.out_proj.weight', 'model.encoder.layers.7.self_attn.out_proj.bias', 'model.encoder.layers.7.self_attn_layer_norm.weight', 'model.encoder.layers.7.self_attn_layer_norm.bias', 'model.encoder.layers.7.fc1.weight', 'model.encoder.layers.7.fc1.bias', 'model.encoder.layers.7.fc2.weight', 'model.encoder.layers.7.fc2.bias', 'model.encoder.layers.7.final_layer_norm.weight', 'model.encoder.layers.7.final_layer_norm.bias', 'model.encoder.layers.8.self_attn.k_proj.weight', 'model.encoder.layers.8.self_attn.v_proj.weight', 'model.encoder.layers.8.self_attn.v_proj.bias', 'model.encoder.layers.8.self_attn.q_proj.weight', 'model.encoder.layers.8.self_attn.q_proj.bias', 'model.encoder.layers.8.self_attn.out_proj.weight', 'model.encoder.layers.8.self_attn.out_proj.bias', 'model.encoder.layers.8.self_attn_layer_norm.weight', 'model.encoder.layers.8.self_attn_layer_norm.bias', 'model.encoder.layers.8.fc1.weight', 'model.encoder.layers.8.fc1.bias', 'model.encoder.layers.8.fc2.weight', 'model.encoder.layers.8.fc2.bias', 'model.encoder.layers.8.final_layer_norm.weight', 'model.encoder.layers.8.final_layer_norm.bias', 'model.encoder.layers.9.self_attn.k_proj.weight', 'model.encoder.layers.9.self_attn.v_proj.weight', 'model.encoder.layers.9.self_attn.v_proj.bias', 'model.encoder.layers.9.self_attn.q_proj.weight', 'model.encoder.layers.9.self_attn.q_proj.bias', 'model.encoder.layers.9.self_attn.out_proj.weight', 'model.encoder.layers.9.self_attn.out_proj.bias', 'model.encoder.layers.9.self_attn_layer_norm.weight', 'model.encoder.layers.9.self_attn_layer_norm.bias', 'model.encoder.layers.9.fc1.weight', 'model.encoder.layers.9.fc1.bias', 'model.encoder.layers.9.fc2.weight', 'model.encoder.layers.9.fc2.bias', 'model.encoder.layers.9.final_layer_norm.weight', 'model.encoder.layers.9.final_layer_norm.bias', 'model.encoder.layers.10.self_attn.k_proj.weight', 'model.encoder.layers.10.self_attn.v_proj.weight', 'model.encoder.layers.10.self_attn.v_proj.bias', 'model.encoder.layers.10.self_attn.q_proj.weight', 'model.encoder.layers.10.self_attn.q_proj.bias', 'model.encoder.layers.10.self_attn.out_proj.weight', 'model.encoder.layers.10.self_attn.out_proj.bias', 'model.encoder.layers.10.self_attn_layer_norm.weight', 'model.encoder.layers.10.self_attn_layer_norm.bias', 'model.encoder.layers.10.fc1.weight', 'model.encoder.layers.10.fc1.bias', 'model.encoder.layers.10.fc2.weight', 'model.encoder.layers.10.fc2.bias', 'model.encoder.layers.10.final_layer_norm.weight', 'model.encoder.layers.10.final_layer_norm.bias', 'model.encoder.layers.11.self_attn.k_proj.weight', 'model.encoder.layers.11.self_attn.v_proj.weight', 'model.encoder.layers.11.self_attn.v_proj.bias', 'model.encoder.layers.11.self_attn.q_proj.weight', 'model.encoder.layers.11.self_attn.q_proj.bias', 'model.encoder.layers.11.self_attn.out_proj.weight', 'model.encoder.layers.11.self_attn.out_proj.bias', 'model.encoder.layers.11.self_attn_layer_norm.weight', 'model.encoder.layers.11.self_attn_layer_norm.bias', 'model.encoder.layers.11.fc1.weight', 'model.encoder.layers.11.fc1.bias', 'model.encoder.layers.11.fc2.weight', 'model.encoder.layers.11.fc2.bias', 'model.encoder.layers.11.final_layer_norm.weight', 'model.encoder.layers.11.final_layer_norm.bias', 'model.encoder.layers.12.self_attn.k_proj.weight', 'model.encoder.layers.12.self_attn.v_proj.weight', 'model.encoder.layers.12.self_attn.v_proj.bias', 'model.encoder.layers.12.self_attn.q_proj.weight', 'model.encoder.layers.12.self_attn.q_proj.bias', 'model.encoder.layers.12.self_attn.out_proj.weight', 'model.encoder.layers.12.self_attn.out_proj.bias', 'model.encoder.layers.12.self_attn_layer_norm.weight', 'model.encoder.layers.12.self_attn_layer_norm.bias', 'model.encoder.layers.12.fc1.weight', 'model.encoder.layers.12.fc1.bias', 'model.encoder.layers.12.fc2.weight', 'model.encoder.layers.12.fc2.bias', 'model.encoder.layers.12.final_layer_norm.weight', 'model.encoder.layers.12.final_layer_norm.bias', 'model.encoder.layers.13.self_attn.k_proj.weight', 'model.encoder.layers.13.self_attn.v_proj.weight', 'model.encoder.layers.13.self_attn.v_proj.bias', 'model.encoder.layers.13.self_attn.q_proj.weight', 'model.encoder.layers.13.self_attn.q_proj.bias', 'model.encoder.layers.13.self_attn.out_proj.weight', 'model.encoder.layers.13.self_attn.out_proj.bias', 'model.encoder.layers.13.self_attn_layer_norm.weight', 'model.encoder.layers.13.self_attn_layer_norm.bias', 'model.encoder.layers.13.fc1.weight', 'model.encoder.layers.13.fc1.bias', 'model.encoder.layers.13.fc2.weight', 'model.encoder.layers.13.fc2.bias', 'model.encoder.layers.13.final_layer_norm.weight', 'model.encoder.layers.13.final_layer_norm.bias', 'model.encoder.layers.14.self_attn.k_proj.weight', 'model.encoder.layers.14.self_attn.v_proj.weight', 'model.encoder.layers.14.self_attn.v_proj.bias', 'model.encoder.layers.14.self_attn.q_proj.weight', 'model.encoder.layers.14.self_attn.q_proj.bias', 'model.encoder.layers.14.self_attn.out_proj.weight', 'model.encoder.layers.14.self_attn.out_proj.bias', 'model.encoder.layers.14.self_attn_layer_norm.weight', 'model.encoder.layers.14.self_attn_layer_norm.bias', 'model.encoder.layers.14.fc1.weight', 'model.encoder.layers.14.fc1.bias', 'model.encoder.layers.14.fc2.weight', 'model.encoder.layers.14.fc2.bias', 'model.encoder.layers.14.final_layer_norm.weight', 'model.encoder.layers.14.final_layer_norm.bias', 'model.encoder.layers.15.self_attn.k_proj.weight', 'model.encoder.layers.15.self_attn.v_proj.weight', 'model.encoder.layers.15.self_attn.v_proj.bias', 'model.encoder.layers.15.self_attn.q_proj.weight', 'model.encoder.layers.15.self_attn.q_proj.bias', 'model.encoder.layers.15.self_attn.out_proj.weight', 'model.encoder.layers.15.self_attn.out_proj.bias', 'model.encoder.layers.15.self_attn_layer_norm.weight', 'model.encoder.layers.15.self_attn_layer_norm.bias', 'model.encoder.layers.15.fc1.weight', 'model.encoder.layers.15.fc1.bias', 'model.encoder.layers.15.fc2.weight', 'model.encoder.layers.15.fc2.bias', 'model.encoder.layers.15.final_layer_norm.weight', 'model.encoder.layers.15.final_layer_norm.bias', 'model.encoder.layers.16.self_attn.k_proj.weight', 'model.encoder.layers.16.self_attn.v_proj.weight', 'model.encoder.layers.16.self_attn.v_proj.bias', 'model.encoder.layers.16.self_attn.q_proj.weight', 'model.encoder.layers.16.self_attn.q_proj.bias', 'model.encoder.layers.16.self_attn.out_proj.weight', 'model.encoder.layers.16.self_attn.out_proj.bias', 'model.encoder.layers.16.self_attn_layer_norm.weight', 'model.encoder.layers.16.self_attn_layer_norm.bias', 'model.encoder.layers.16.fc1.weight', 'model.encoder.layers.16.fc1.bias', 'model.encoder.layers.16.fc2.weight', 'model.encoder.layers.16.fc2.bias', 'model.encoder.layers.16.final_layer_norm.weight', 'model.encoder.layers.16.final_layer_norm.bias', 'model.encoder.layers.17.self_attn.k_proj.weight', 'model.encoder.layers.17.self_attn.v_proj.weight', 'model.encoder.layers.17.self_attn.v_proj.bias', 'model.encoder.layers.17.self_attn.q_proj.weight', 'model.encoder.layers.17.self_attn.q_proj.bias', 'model.encoder.layers.17.self_attn.out_proj.weight', 'model.encoder.layers.17.self_attn.out_proj.bias', 'model.encoder.layers.17.self_attn_layer_norm.weight', 'model.encoder.layers.17.self_attn_layer_norm.bias', 'model.encoder.layers.17.fc1.weight', 'model.encoder.layers.17.fc1.bias', 'model.encoder.layers.17.fc2.weight', 'model.encoder.layers.17.fc2.bias', 'model.encoder.layers.17.final_layer_norm.weight', 'model.encoder.layers.17.final_layer_norm.bias', 'model.encoder.layers.18.self_attn.k_proj.weight', 'model.encoder.layers.18.self_attn.v_proj.weight', 'model.encoder.layers.18.self_attn.v_proj.bias', 'model.encoder.layers.18.self_attn.q_proj.weight', 'model.encoder.layers.18.self_attn.q_proj.bias', 'model.encoder.layers.18.self_attn.out_proj.weight', 'model.encoder.layers.18.self_attn.out_proj.bias', 'model.encoder.layers.18.self_attn_layer_norm.weight', 'model.encoder.layers.18.self_attn_layer_norm.bias', 'model.encoder.layers.18.fc1.weight', 'model.encoder.layers.18.fc1.bias', 'model.encoder.layers.18.fc2.weight', 'model.encoder.layers.18.fc2.bias', 'model.encoder.layers.18.final_layer_norm.weight', 'model.encoder.layers.18.final_layer_norm.bias', 'model.encoder.layers.19.self_attn.k_proj.weight', 'model.encoder.layers.19.self_attn.v_proj.weight', 'model.encoder.layers.19.self_attn.v_proj.bias', 'model.encoder.layers.19.self_attn.q_proj.weight', 'model.encoder.layers.19.self_attn.q_proj.bias', 'model.encoder.layers.19.self_attn.out_proj.weight', 'model.encoder.layers.19.self_attn.out_proj.bias', 'model.encoder.layers.19.self_attn_layer_norm.weight', 'model.encoder.layers.19.self_attn_layer_norm.bias', 'model.encoder.layers.19.fc1.weight', 'model.encoder.layers.19.fc1.bias', 'model.encoder.layers.19.fc2.weight', 'model.encoder.layers.19.fc2.bias', 'model.encoder.layers.19.final_layer_norm.weight', 'model.encoder.layers.19.final_layer_norm.bias', 'model.encoder.layers.20.self_attn.k_proj.weight', 'model.encoder.layers.20.self_attn.v_proj.weight', 'model.encoder.layers.20.self_attn.v_proj.bias', 'model.encoder.layers.20.self_attn.q_proj.weight', 'model.encoder.layers.20.self_attn.q_proj.bias', 'model.encoder.layers.20.self_attn.out_proj.weight', 'model.encoder.layers.20.self_attn.out_proj.bias', 'model.encoder.layers.20.self_attn_layer_norm.weight', 'model.encoder.layers.20.self_attn_layer_norm.bias', 'model.encoder.layers.20.fc1.weight', 'model.encoder.layers.20.fc1.bias', 'model.encoder.layers.20.fc2.weight', 'model.encoder.layers.20.fc2.bias', 'model.encoder.layers.20.final_layer_norm.weight', 'model.encoder.layers.20.final_layer_norm.bias', 'model.encoder.layers.21.self_attn.k_proj.weight', 'model.encoder.layers.21.self_attn.v_proj.weight', 'model.encoder.layers.21.self_attn.v_proj.bias', 'model.encoder.layers.21.self_attn.q_proj.weight', 'model.encoder.layers.21.self_attn.q_proj.bias', 'model.encoder.layers.21.self_attn.out_proj.weight', 'model.encoder.layers.21.self_attn.out_proj.bias', 'model.encoder.layers.21.self_attn_layer_norm.weight', 'model.encoder.layers.21.self_attn_layer_norm.bias', 'model.encoder.layers.21.fc1.weight', 'model.encoder.layers.21.fc1.bias', 'model.encoder.layers.21.fc2.weight', 'model.encoder.layers.21.fc2.bias', 'model.encoder.layers.21.final_layer_norm.weight', 'model.encoder.layers.21.final_layer_norm.bias', 'model.encoder.layers.22.self_attn.k_proj.weight', 'model.encoder.layers.22.self_attn.v_proj.weight', 'model.encoder.layers.22.self_attn.v_proj.bias', 'model.encoder.layers.22.self_attn.q_proj.weight', 'model.encoder.layers.22.self_attn.q_proj.bias', 'model.encoder.layers.22.self_attn.out_proj.weight', 'model.encoder.layers.22.self_attn.out_proj.bias', 'model.encoder.layers.22.self_attn_layer_norm.weight', 'model.encoder.layers.22.self_attn_layer_norm.bias', 'model.encoder.layers.22.fc1.weight', 'model.encoder.layers.22.fc1.bias', 'model.encoder.layers.22.fc2.weight', 'model.encoder.layers.22.fc2.bias', 'model.encoder.layers.22.final_layer_norm.weight', 'model.encoder.layers.22.final_layer_norm.bias', 'model.encoder.layers.23.self_attn.k_proj.weight', 'model.encoder.layers.23.self_attn.v_proj.weight', 'model.encoder.layers.23.self_attn.v_proj.bias', 'model.encoder.layers.23.self_attn.q_proj.weight', 'model.encoder.layers.23.self_attn.q_proj.bias', 'model.encoder.layers.23.self_attn.out_proj.weight', 'model.encoder.layers.23.self_attn.out_proj.bias', 'model.encoder.layers.23.self_attn_layer_norm.weight', 'model.encoder.layers.23.self_attn_layer_norm.bias', 'model.encoder.layers.23.fc1.weight', 'model.encoder.layers.23.fc1.bias', 'model.encoder.layers.23.fc2.weight', 'model.encoder.layers.23.fc2.bias', 'model.encoder.layers.23.final_layer_norm.weight', 'model.encoder.layers.23.final_layer_norm.bias', 'model.encoder.layers.24.self_attn.k_proj.weight', 'model.encoder.layers.24.self_attn.v_proj.weight', 'model.encoder.layers.24.self_attn.v_proj.bias', 'model.encoder.layers.24.self_attn.q_proj.weight', 'model.encoder.layers.24.self_attn.q_proj.bias', 'model.encoder.layers.24.self_attn.out_proj.weight', 'model.encoder.layers.24.self_attn.out_proj.bias', 'model.encoder.layers.24.self_attn_layer_norm.weight', 'model.encoder.layers.24.self_attn_layer_norm.bias', 'model.encoder.layers.24.fc1.weight', 'model.encoder.layers.24.fc1.bias', 'model.encoder.layers.24.fc2.weight', 'model.encoder.layers.24.fc2.bias', 'model.encoder.layers.24.final_layer_norm.weight', 'model.encoder.layers.24.final_layer_norm.bias', 'model.encoder.layers.25.self_attn.k_proj.weight', 'model.encoder.layers.25.self_attn.v_proj.weight', 'model.encoder.layers.25.self_attn.v_proj.bias', 'model.encoder.layers.25.self_attn.q_proj.weight', 'model.encoder.layers.25.self_attn.q_proj.bias', 'model.encoder.layers.25.self_attn.out_proj.weight', 'model.encoder.layers.25.self_attn.out_proj.bias', 'model.encoder.layers.25.self_attn_layer_norm.weight', 'model.encoder.layers.25.self_attn_layer_norm.bias', 'model.encoder.layers.25.fc1.weight', 'model.encoder.layers.25.fc1.bias', 'model.encoder.layers.25.fc2.weight', 'model.encoder.layers.25.fc2.bias', 'model.encoder.layers.25.final_layer_norm.weight', 'model.encoder.layers.25.final_layer_norm.bias', 'model.encoder.layers.26.self_attn.k_proj.weight', 'model.encoder.layers.26.self_attn.v_proj.weight', 'model.encoder.layers.26.self_attn.v_proj.bias', 'model.encoder.layers.26.self_attn.q_proj.weight', 'model.encoder.layers.26.self_attn.q_proj.bias', 'model.encoder.layers.26.self_attn.out_proj.weight', 'model.encoder.layers.26.self_attn.out_proj.bias', 'model.encoder.layers.26.self_attn_layer_norm.weight', 'model.encoder.layers.26.self_attn_layer_norm.bias', 'model.encoder.layers.26.fc1.weight', 'model.encoder.layers.26.fc1.bias', 'model.encoder.layers.26.fc2.weight', 'model.encoder.layers.26.fc2.bias', 'model.encoder.layers.26.final_layer_norm.weight', 'model.encoder.layers.26.final_layer_norm.bias', 'model.encoder.layers.27.self_attn.k_proj.weight', 'model.encoder.layers.27.self_attn.v_proj.weight', 'model.encoder.layers.27.self_attn.v_proj.bias', 'model.encoder.layers.27.self_attn.q_proj.weight', 'model.encoder.layers.27.self_attn.q_proj.bias', 'model.encoder.layers.27.self_attn.out_proj.weight', 'model.encoder.layers.27.self_attn.out_proj.bias', 'model.encoder.layers.27.self_attn_layer_norm.weight', 'model.encoder.layers.27.self_attn_layer_norm.bias', 'model.encoder.layers.27.fc1.weight', 'model.encoder.layers.27.fc1.bias', 'model.encoder.layers.27.fc2.weight', 'model.encoder.layers.27.fc2.bias', 'model.encoder.layers.27.final_layer_norm.weight', 'model.encoder.layers.27.final_layer_norm.bias', 'model.encoder.layers.28.self_attn.k_proj.weight', 'model.encoder.layers.28.self_attn.v_proj.weight', 'model.encoder.layers.28.self_attn.v_proj.bias', 'model.encoder.layers.28.self_attn.q_proj.weight', 'model.encoder.layers.28.self_attn.q_proj.bias', 'model.encoder.layers.28.self_attn.out_proj.weight', 'model.encoder.layers.28.self_attn.out_proj.bias', 'model.encoder.layers.28.self_attn_layer_norm.weight', 'model.encoder.layers.28.self_attn_layer_norm.bias', 'model.encoder.layers.28.fc1.weight', 'model.encoder.layers.28.fc1.bias', 'model.encoder.layers.28.fc2.weight', 'model.encoder.layers.28.fc2.bias', 'model.encoder.layers.28.final_layer_norm.weight', 'model.encoder.layers.28.final_layer_norm.bias', 'model.encoder.layers.29.self_attn.k_proj.weight', 'model.encoder.layers.29.self_attn.v_proj.weight', 'model.encoder.layers.29.self_attn.v_proj.bias', 'model.encoder.layers.29.self_attn.q_proj.weight', 'model.encoder.layers.29.self_attn.q_proj.bias', 'model.encoder.layers.29.self_attn.out_proj.weight', 'model.encoder.layers.29.self_attn.out_proj.bias', 'model.encoder.layers.29.self_attn_layer_norm.weight', 'model.encoder.layers.29.self_attn_layer_norm.bias', 'model.encoder.layers.29.fc1.weight', 'model.encoder.layers.29.fc1.bias', 'model.encoder.layers.29.fc2.weight', 'model.encoder.layers.29.fc2.bias', 'model.encoder.layers.29.final_layer_norm.weight', 'model.encoder.layers.29.final_layer_norm.bias', 'model.encoder.layers.30.self_attn.k_proj.weight', 'model.encoder.layers.30.self_attn.v_proj.weight', 'model.encoder.layers.30.self_attn.v_proj.bias', 'model.encoder.layers.30.self_attn.q_proj.weight', 'model.encoder.layers.30.self_attn.q_proj.bias', 'model.encoder.layers.30.self_attn.out_proj.weight', 'model.encoder.layers.30.self_attn.out_proj.bias', 'model.encoder.layers.30.self_attn_layer_norm.weight', 'model.encoder.layers.30.self_attn_layer_norm.bias', 'model.encoder.layers.30.fc1.weight', 'model.encoder.layers.30.fc1.bias', 'model.encoder.layers.30.fc2.weight', 'model.encoder.layers.30.fc2.bias', 'model.encoder.layers.30.final_layer_norm.weight', 'model.encoder.layers.30.final_layer_norm.bias', 'model.encoder.layers.31.self_attn.k_proj.weight', 'model.encoder.layers.31.self_attn.v_proj.weight', 'model.encoder.layers.31.self_attn.v_proj.bias', 'model.encoder.layers.31.self_attn.q_proj.weight', 'model.encoder.layers.31.self_attn.q_proj.bias', 'model.encoder.layers.31.self_attn.out_proj.weight', 'model.encoder.layers.31.self_attn.out_proj.bias', 'model.encoder.layers.31.self_attn_layer_norm.weight', 'model.encoder.layers.31.self_attn_layer_norm.bias', 'model.encoder.layers.31.fc1.weight', 'model.encoder.layers.31.fc1.bias', 'model.encoder.layers.31.fc2.weight', 'model.encoder.layers.31.fc2.bias', 'model.encoder.layers.31.final_layer_norm.weight', 'model.encoder.layers.31.final_layer_norm.bias']

sanchit-gandhi commented 6 months ago

Hey @Eskaggg, thanks for reporting! Could you confirm that you've made no changes to the file create_student_model.py? And subsequently, what the bash command is that you're using to run this script? e.g. like the template on the README:

#!/usr/bin/env bash

python create_student_model.py \
  --teacher_checkpoint "openai/whisper-large-v2" \
  --encoder_layers 32 \
  --decoder_layers 2 \
  --save_dir "./distil-large-v2-init"

And finally: could you please share the output of this command:

transformers-cli env

Many thanks!

Eskaggg commented 6 months ago

@sanchit-gandhi Tnks for reply (output) transformers-cli env:

Eskaggg commented 6 months ago

And another error is here :

loading file vocab.json loading file tokenizer.json loading file merges.txt loading file normalizer.json loading file added_tokens.json loading file special_tokens_map.json loading file tokenizer_config.json Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 12/20/2023 11:49:18 - INFO - main - max_steps is given, it will override any value given in num_train_epochs 12/20/2023 11:49:19 - INFO - main - Running training 12/20/2023 11:49:19 - INFO - main - Num examples = 40000 12/20/2023 11:49:19 - INFO - main - Instantaneous batch size per device = 8 12/20/2023 11:49:19 - INFO - main - Gradient accumulation steps = 1 12/20/2023 11:49:19 - INFO - main - Total train batch size (w. parallel & distributed) = 8 12/20/2023 11:49:19 - INFO - main - Total optimization steps = 5000 Train steps ... : 0%| | 0/5000 [00:00<?, ?it/s]Traceback (most recent call last): File "/home/codelex/Documents/lawly/linear_regression/distil-whisper/training/Distil-whisper-mn/run_distillation.py", line 1631, in main() File "/home/codelex/Documents/lawly/linear_regression/distil-whisper/training/Distil-whisper-mn/run_distillation.py", line 1489, in main loss, train_metric = train_step(batch, temperature=training_args.temperature) File "/home/codelex/Documents/lawly/linear_regression/distil-whisper/training/Distil-whisper-mn/run_distillation.py", line 1357, in train_step student_outputs = student_model(batch) TypeError: WhisperForConditionalGeneration( (model): WhisperModel( (encoder): WhisperEncoder( (conv1): Conv1d(80, 1280, kernel_size=(3,), stride=(1,), padding=(1,)) (conv2): Conv1d(1280, 1280, kernel_size=(3,), stride=(2,), padding=(1,)) (embed_positions): Embedding(1500, 1280) (layers): ModuleList( (0-31): 32 x WhisperEncoderLayer( (self_attn): WhisperAttention( (k_proj): Linear(in_features=1280, out_features=1280, bias=False) (v_proj): Linear(in_features=1280, out_features=1280, bias=True) (q_proj): Linear(in_features=1280, out_features=1280, bias=True) (out_proj): Linear(in_features=1280, out_features=1280, bias=True) ) (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) (activation_fn): GELUActivation() (fc1): Linear(in_features=1280, out_features=5120, bias=True) (fc2): Linear(in_features=5120, out_features=1280, bias=True) (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) ) ) (layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) ) (decoder): WhisperDecoder( (embed_tokens): Embedding(51865, 1280, padding_idx=50257) (embed_positions): WhisperPositionalEmbedding(448, 1280) (layers): ModuleList( (0-1): 2 x WhisperDecoderLayer( (self_attn): WhisperAttention( (k_proj): Linear(in_features=1280, out_features=1280, bias=False) (v_proj): Linear(in_features=1280, out_features=1280, bias=True) (q_proj): Linear(in_features=1280, out_features=1280, bias=True) (out_proj): Linear(in_features=1280, out_features=1280, bias=True) ) (activation_fn): GELUActivation() (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) (encoder_attn): WhisperAttention( (k_proj): Linear(in_features=1280, out_features=1280, bias=False) (v_proj): Linear(in_features=1280, out_features=1280, bias=True) (q_proj): Linear(in_features=1280, out_features=1280, bias=True) (out_proj): Linear(in_features=1280, out_features=1280, bias=True) ) (encoder_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) (fc1): Linear(in_features=1280, out_features=5120, bias=True) (fc2): Linear(in_features=5120, out_features=1280, bias=True) (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) ) ) (layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True) ) ) (proj_out): Linear(in_features=1280, out_features=51865, bias=False) ) argument after must be a mapping, not NoneType

sanchit-gandhi commented 5 months ago

Hey @Eskaggg - could you please give the command that you're using to initialise the student model, as requested previously? It would be super helpful if I could run this locally on my side to find the error. Thanks!