Hugging Face's logo

ImanNalia
/
base

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ImanNalia commited on
Commit
bc03e11
•
1 Parent(s): 2cd4332

ImanNalia/FT_Wav2Vec2_Base_No_LM_V2

Browse files
Files changed (4) hide show
  1. README.md +9 -9
  2. model.safetensors +1 -1
  3. runs/Apr07_07-37-45_n8ew6p6lio/events.out.tfevents.1712475559.n8ew6p6lio.129.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.7496
21
- - Wer: 45.8524
22
- - Cer: 23.3228
23
 
24
  ## Model description
25
 
@@ -45,17 +45,17 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 2000
48
- - training_steps: 5000
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
54
- | 3.3189 | 18.52 | 1000 | 1.3203 | 61.7505 | 28.6087 |
55
- | 0.4697 | 37.04 | 2000 | 1.3792 | 48.5805 | 24.3342 |
56
- | 0.1681 | 55.56 | 3000 | 1.4859 | 47.0433 | 23.6677 |
57
- | 0.0913 | 74.07 | 4000 | 1.6549 | 46.4617 | 23.4416 |
58
- | 0.0598 | 92.59 | 5000 | 1.7496 | 45.8524 | 23.3228 |
59
 
60
 
61
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.4338
21
+ - Wer: 46.6971
22
+ - Cer: 23.6416
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 2000
48
+ - num_epochs: 50
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
54
+ | 4.2769 | 9.26 | 500 | 2.9188 | 99.9308 | 99.1103 |
55
+ | 2.4426 | 18.52 | 1000 | 1.2869 | 64.5340 | 29.9360 |
56
+ | 0.65 | 27.78 | 1500 | 1.2520 | 49.7577 | 24.1951 |
57
+ | 0.3121 | 37.04 | 2000 | 1.3616 | 49.4391 | 24.7776 |
58
+ | 0.187 | 46.3 | 2500 | 1.4338 | 46.6971 | 23.6416 |
59
 
60
 
61
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d23c8e21d37825577711ad0199f3878b796efab31a8f8e6af4e3008f00613aef
3
  size 377611072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8338d66a3bc159a7e49299b4d11d3cec4e8ccf7a8c416ed95dc5b3b8222d9703
3
  size 377611072
runs/Apr07_07-37-45_n8ew6p6lio/events.out.tfevents.1712475559.n8ew6p6lio.129.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2921f3bf628940c63da1e0c870cf7fbb8715440335d52e07cf755f9b726061fd
3
+ size 9860
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:814b47f654ff1adcea5b4726444ad0eb759bc5787a38d6d9dea582304a1e2351
3
  size 4527
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a13390488f07918d304364c62c0fc2a237a0263fddfc9443c017648041c69bc
3
  size 4527