Hugging Face's logo

henilp105
/
wav2vec2-large-xls-r-300m-telugu-asr

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
henil panchal commited on
Commit
e503bab
•
1 Parent(s): 6246b91

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -16
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [henilp105/wav2vec2-large-xls-r-300m-telugu-asr](https://huggingface.co/henilp105/wav2vec2-large-xls-r-300m-telugu-asr) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 4.0959
20
- - Wer: 1.0406
21
 
22
  ## Model description
23
 
@@ -52,20 +52,19 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 3.6321 | 2.04 | 200 | 2.3063 | 0.9872 |
56
- | 1.8629 | 4.08 | 400 | 2.4143 | 0.9926 |
57
- | 1.3881 | 6.12 | 600 | 2.5862 | 0.9795 |
58
- | 1.0565 | 8.16 | 800 | 2.6708 | 1.0191 |
59
- | 0.7681 | 10.2 | 1000 | 3.1001 | 0.9992 |
60
- | 0.5867 | 12.24 | 1200 | 3.4503 | 1.0228 |
61
- | 0.4289 | 14.29 | 1400 | 3.5382 | 1.0165 |
62
- | 0.3618 | 16.33 | 1600 | 3.5116 | 0.9835 |
63
- | 0.3229 | 18.37 | 1800 | 3.6524 | 1.0093 |
64
- | 0.2483 | 20.41 | 2000 | 3.6222 | 1.0319 |
65
- | 0.2215 | 22.45 | 2200 | 3.9824 | 1.0414 |
66
- | 0.1833 | 24.49 | 2400 | 3.9272 | 1.0393 |
67
- | 0.1706 | 26.53 | 2600 | 3.9290 | 1.0425 |
68
- | 0.1463 | 28.57 | 2800 | 4.0959 | 1.0406 |
69
 
70
 
71
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [henilp105/wav2vec2-large-xls-r-300m-telugu-asr](https://huggingface.co/henilp105/wav2vec2-large-xls-r-300m-telugu-asr) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: inf
20
+ - Wer: 0.8094
21
 
22
  ## Model description
23
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 3.3952 | 2.3 | 200 | inf | 0.9316 |
56
+ | 0.9044 | 4.59 | 400 | inf | 0.8832 |
57
+ | 0.5208 | 6.89 | 600 | inf | 0.8467 |
58
+ | 0.3552 | 9.19 | 800 | inf | 0.8444 |
59
+ | 0.259 | 11.49 | 1000 | inf | 0.84 |
60
+ | 0.2113 | 13.79 | 1200 | inf | 0.8321 |
61
+ | 0.1681 | 16.09 | 1400 | inf | 0.8264 |
62
+ | 0.1468 | 18.39 | 1600 | inf | 0.8281 |
63
+ | 0.1321 | 20.69 | 1800 | inf | 0.8198 |
64
+ | 0.1167 | 22.98 | 2000 | inf | 0.7958 |
65
+ | 0.1028 | 25.29 | 2200 | inf | 0.8007 |
66
+ | 0.0947 | 27.58 | 2400 | inf | 0.8035 |
67
+ | 0.0829 | 29.88 | 2600 | inf | 0.8094 |
 
68
 
69
 
70
  ### Framework versions