Hugging Face's logo

infinitejoy
/
wav2vec2-large-xls-r-300m-greek

Automatic Speech Recognition
Transformers
PyTorch
Greek
wav2vec2
mozilla-foundation/common_voice_7_0
Generated from Trainer
robust-speech-event
model_for_talk
hf-asr-leaderboard
Eval Results
Inference Endpoints
Model card Files Community
1
infinitejoy commited on
Commit
c0b88d5
•
1 Parent(s): b44f7f3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -24
README.md CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - EL dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.6831
24
- - Wer: 0.4287
25
 
26
  ## Model description
27
 
@@ -54,28 +54,28 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
57
- | 3.0798 | 4.42 | 500 | 3.0010 | 1.0012 |
58
- | 1.4336 | 8.85 | 1000 | 0.8481 | 0.6911 |
59
- | 1.2062 | 13.27 | 1500 | 0.7312 | 0.6333 |
60
- | 1.0481 | 17.7 | 2000 | 0.6850 | 0.5359 |
61
- | 0.9837 | 22.12 | 2500 | 0.6337 | 0.5316 |
62
- | 0.9108 | 26.55 | 3000 | 0.6258 | 0.5079 |
63
- | 0.8439 | 30.97 | 3500 | 0.6301 | 0.4888 |
64
- | 0.7901 | 35.4 | 4000 | 0.6245 | 0.4977 |
65
- | 0.7669 | 39.82 | 4500 | 0.6164 | 0.4672 |
66
- | 0.7196 | 44.25 | 5000 | 0.6039 | 0.4688 |
67
- | 0.6715 | 48.67 | 5500 | 0.5900 | 0.4573 |
68
- | 0.6441 | 53.1 | 6000 | 0.7002 | 0.4798 |
69
- | 0.5938 | 57.52 | 6500 | 0.6249 | 0.4579 |
70
- | 0.5541 | 61.95 | 7000 | 0.6184 | 0.4425 |
71
- | 0.5506 | 66.37 | 7500 | 0.6963 | 0.4585 |
72
- | 0.4998 | 70.8 | 8000 | 0.6778 | 0.4468 |
73
- | 0.4729 | 75.22 | 8500 | 0.6383 | 0.4393 |
74
- | 0.4535 | 79.65 | 9000 | 0.6593 | 0.4369 |
75
- | 0.4358 | 84.07 | 9500 | 0.6914 | 0.4422 |
76
- | 0.402 | 88.5 | 10000 | 0.6744 | 0.4269 |
77
- | 0.3946 | 92.92 | 10500 | 0.6895 | 0.4275 |
78
- | 0.3734 | 97.35 | 11000 | 0.6889 | 0.4320 |
79
 
80
 
81
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - EL dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.6592
24
+ - Wer: 0.4564
25
 
26
  ## Model description
27
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
57
+ | 3.0928 | 4.42 | 500 | 3.0804 | 1.0073 |
58
+ | 1.4505 | 8.85 | 1000 | 0.9038 | 0.7330 |
59
+ | 1.2207 | 13.27 | 1500 | 0.7375 | 0.6045 |
60
+ | 1.0695 | 17.7 | 2000 | 0.7119 | 0.5441 |
61
+ | 1.0104 | 22.12 | 2500 | 0.6069 | 0.5296 |
62
+ | 0.9299 | 26.55 | 3000 | 0.6168 | 0.5206 |
63
+ | 0.8588 | 30.97 | 3500 | 0.6382 | 0.5171 |
64
+ | 0.7942 | 35.4 | 4000 | 0.6048 | 0.4988 |
65
+ | 0.7808 | 39.82 | 4500 | 0.6730 | 0.5084 |
66
+ | 0.743 | 44.25 | 5000 | 0.6749 | 0.5012 |
67
+ | 0.6652 | 48.67 | 5500 | 0.6491 | 0.4735 |
68
+ | 0.6386 | 53.1 | 6000 | 0.6928 | 0.4954 |
69
+ | 0.5945 | 57.52 | 6500 | 0.6359 | 0.4798 |
70
+ | 0.5561 | 61.95 | 7000 | 0.6409 | 0.4799 |
71
+ | 0.5464 | 66.37 | 7500 | 0.6452 | 0.4691 |
72
+ | 0.5119 | 70.8 | 8000 | 0.6376 | 0.4657 |
73
+ | 0.474 | 75.22 | 8500 | 0.6541 | 0.4700 |
74
+ | 0.45 | 79.65 | 9000 | 0.6374 | 0.4571 |
75
+ | 0.4315 | 84.07 | 9500 | 0.6568 | 0.4625 |
76
+ | 0.3967 | 88.5 | 10000 | 0.6636 | 0.4605 |
77
+ | 0.3937 | 92.92 | 10500 | 0.6537 | 0.4597 |
78
+ | 0.3788 | 97.35 | 11000 | 0.6614 | 0.4589 |
79
 
80
 
81
  ### Framework versions