Hugging Face's logo

gary109
/
ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
gary109/AI_Light_Dance
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram / README.md
gary109's picture
gary109
update model card README.md
586b315
preview code
|
raw
history blame
7.75 kB
metadata
license: apache-2.0
tags:
  - automatic-speech-recognition
  - gary109/AI_Light_Dance
  - generated_from_trainer
model-index:
  - name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram
    results: []

ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram

This model is a fine-tuned version of gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING3 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4498
  • Wer: 0.2114

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-06
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 100.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.341 1.0 144 0.4498 0.2114
0.306 2.0 288 0.4533 0.2128
0.3028 3.0 432 0.4555 0.2096
0.2994 4.0 576 0.4597 0.2098
0.3033 5.0 720 0.4625 0.2096
0.2944 6.0 864 0.4617 0.2085
0.2836 7.0 1008 0.4615 0.2081
0.3034 8.0 1152 0.4636 0.2077
0.2979 9.0 1296 0.4661 0.2083
0.2967 10.0 1440 0.4644 0.2072
0.2974 11.0 1584 0.4641 0.2077
0.3053 12.0 1728 0.4654 0.2078
0.2927 13.0 1872 0.4682 0.2071
0.282 14.0 2016 0.4660 0.2066
0.299 15.0 2160 0.4671 0.2072
0.3152 16.0 2304 0.4653 0.2051
0.288 17.0 2448 0.4656 0.2062
0.303 18.0 2592 0.4702 0.2050
0.2943 19.0 2736 0.4695 0.2069
0.2735 20.0 2880 0.4715 0.2072
0.3044 21.0 3024 0.4715 0.2049
0.3019 22.0 3168 0.4655 0.2051
0.303 23.0 3312 0.4669 0.2047
0.2846 24.0 3456 0.4657 0.2047
0.2982 25.0 3600 0.4666 0.2041
0.3087 26.0 3744 0.4677 0.2031
0.2954 27.0 3888 0.4670 0.2044
0.2884 28.0 4032 0.4667 0.2046
0.2979 29.0 4176 0.4691 0.2063
0.298 30.0 4320 0.4648 0.2039
0.2963 31.0 4464 0.4648 0.2057
0.3047 32.0 4608 0.4688 0.2052
0.3 33.0 4752 0.4698 0.2051
0.2883 34.0 4896 0.4655 0.2042
0.2936 35.0 5040 0.4683 0.2043
0.2868 36.0 5184 0.4677 0.2046
0.2935 37.0 5328 0.4665 0.2046
0.2883 38.0 5472 0.4680 0.2022
0.296 39.0 5616 0.4685 0.2033
0.2967 40.0 5760 0.4663 0.2038
0.2909 41.0 5904 0.4634 0.2046
0.2834 42.0 6048 0.4636 0.2042
0.2904 43.0 6192 0.4700 0.2038
0.3006 44.0 6336 0.4670 0.2029
0.281 45.0 6480 0.4705 0.2030
0.2964 46.0 6624 0.4704 0.2016
0.2914 47.0 6768 0.4644 0.2013
0.2948 48.0 6912 0.4693 0.2027
0.2904 49.0 7056 0.4687 0.2015
0.2875 50.0 7200 0.4730 0.2017
0.2889 51.0 7344 0.4693 0.2011
0.2829 52.0 7488 0.4681 0.2011
0.296 53.0 7632 0.4675 0.2002
0.3022 54.0 7776 0.4720 0.2008
0.2813 55.0 7920 0.4702 0.2019
0.2988 56.0 8064 0.4706 0.2027
0.2942 57.0 8208 0.4718 0.2025
0.2899 58.0 8352 0.4729 0.2008
0.2844 59.0 8496 0.4744 0.2006
0.2749 60.0 8640 0.4720 0.2011
0.2835 61.0 8784 0.4718 0.2017
0.2908 62.0 8928 0.4702 0.2014
0.2834 63.0 9072 0.4699 0.2022
0.3023 64.0 9216 0.4667 0.2010
0.2814 65.0 9360 0.4657 0.2007
0.2775 66.0 9504 0.4680 0.2015
0.2991 67.0 9648 0.4656 0.2016
0.2952 68.0 9792 0.4685 0.2008
0.2874 69.0 9936 0.4686 0.2013
0.2951 70.0 10080 0.4693 0.2011
0.2952 71.0 10224 0.4699 0.2004
0.2986 72.0 10368 0.4711 0.2011
0.2858 73.0 10512 0.4660 0.2008
0.3033 74.0 10656 0.4656 0.2004
0.2791 75.0 10800 0.4654 0.2011
0.2971 76.0 10944 0.4645 0.2006
0.2816 77.0 11088 0.4645 0.2006
0.274 78.0 11232 0.4652 0.2001
0.2924 79.0 11376 0.4655 0.2007
0.299 80.0 11520 0.4642 0.2004
0.3009 81.0 11664 0.4652 0.1998
0.281 82.0 11808 0.4691 0.2009
0.2969 83.0 11952 0.4695 0.2002
0.2896 84.0 12096 0.4694 0.2005
0.2918 85.0 12240 0.4701 0.2003
0.2897 86.0 12384 0.4702 0.2000
0.2968 87.0 12528 0.4702 0.2004
0.2992 88.0 12672 0.4689 0.2013
0.2813 89.0 12816 0.4691 0.2009
0.283 90.0 12960 0.4696 0.1999
0.2915 91.0 13104 0.4692 0.2007
0.2867 92.0 13248 0.4677 0.2011
0.2922 93.0 13392 0.4678 0.1998
0.2846 94.0 13536 0.4663 0.2008
0.2867 95.0 13680 0.4657 0.1996
0.2912 96.0 13824 0.4660 0.1998
0.2752 97.0 13968 0.4658 0.2001
0.2914 98.0 14112 0.4661 0.2010
0.2826 99.0 14256 0.4655 0.2003
0.2839 100.0 14400 0.4664 0.1998

Framework versions

  • Transformers 4.21.0.dev0
  • Pytorch 1.9.1+cu102
  • Datasets 2.3.3.dev0
  • Tokenizers 0.12.1