Hugging Face's logo

Akaash1
/
training

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
Akaash1 commited on
Commit
81792fc
·
verified ·
1 Parent(s): e578165

End of training

Browse files
Files changed (5) hide show
  1. README.md +11 -12
  2. adapter.khm.safetensors +1 -1
  3. model.safetensors +1 -1
  4. runs/Dec17_21-33-16_Hong/events.out.tfevents.1765981996.Hong +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: inf
22
- - Wer: 0.6708
23
 
24
  ## Model description
25
 
@@ -38,12 +38,10 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 0.0003
42
  - train_batch_size: 4
43
  - eval_batch_size: 8
44
  - seed: 42
45
- - gradient_accumulation_steps: 2
46
- - total_train_batch_size: 8
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 500
@@ -54,13 +52,14 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:------:|:----:|:---------------:|:------:|
57
- | 8.5386 | 0.9852 | 500 | 0.9350 | 0.6554 |
58
- | 2.1625 | 1.9695 | 1000 | 0.8697 | 0.6609 |
59
- | 2.3315 | 2.9537 | 1500 | 1.0419 | 0.7250 |
60
- | 2.6960 | 3.9379 | 2000 | 1.1913 | 0.7419 |
61
- | 2.8073 | 4.9222 | 2500 | 1.1913 | 0.7419 |
62
- | 2.8293 | 5.9064 | 3000 | 1.1912 | 0.7419 |
63
- | 2.8210 | 6.8906 | 3500 | 1.1912 | 0.7420 |
 
64
 
65
 
66
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 22.6258
22
+ - Wer: 0.9999
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 0.001
42
  - train_batch_size: 4
43
  - eval_batch_size: 8
44
  - seed: 42
 
 
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 2.9169 | 0.4926 | 500 | 0.9563 | 0.6717 |
56
+ | 1.1420 | 0.9852 | 1000 | 0.9029 | 0.6855 |
57
+ | 0.9580 | 1.4778 | 1500 | 0.8356 | 0.6427 |
58
+ | 1.1198 | 1.9704 | 2000 | 0.8504 | 0.6769 |
59
+ | 1.6392 | 2.4631 | 2500 | 3.2183 | 1.0 |
60
+ | 6.0871 | 2.9557 | 3000 | 14.2035 | 1.0315 |
61
+ | 25.2255 | 3.4483 | 3500 | 22.6256 | 0.9999 |
62
+ | 22.4894 | 3.9409 | 4000 | 22.6258 | 0.9999 |
63
 
64
 
65
  ### Framework versions
adapter.khm.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fb31ed3acb7b7cb304efb4b3e7099345c65ae661dfe8906cc98952bbf7c44bc
3
  size 9162368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20706e75773ce132619bd8d6fecbd3e2685bb2893ef6c4b56bb24632aae4ba1
3
  size 9162368
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:865a2c887be6740bd841ae884f15d503b7b29afe137fc71f196354e468432322
3
  size 3859254680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:164362f7e5aeaf3db122c877d43275e87cbe1b79baebd7f39c0474646db2e1e8
3
  size 3859254680
runs/Dec17_21-33-16_Hong/events.out.tfevents.1765981996.Hong ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcdfb2c8d3f8d5e2f504a6c57a64e49cddf32d1403b5ca5e79b68509cdc23e0a
3
+ size 10225
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecae0ec30b027ddb08c326e5db180960f8048e078ccaeb24531fb2b762144a89
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bb520140b6e1cb71e669ce7c3ebb14a3b966536e23b53b856f2a23f2741e26b
3
  size 4792