Hugging Face's logo

Rafaelrosendo1
/
whisper-large-pt

Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
Rafaelrosendo1 commited on
Commit
58bae43
•
1 Parent(s): 0f73713

Rafaelrosendo1/whisper_small_teste

Browse files
Files changed (4) hide show
  1. README.md +10 -10
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: openai/whisper-large
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # whisper-large-pt
17
 
18
- This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1654
21
- - Wer: 39.7172
22
 
23
  ## Model description
24
 
@@ -37,8 +37,8 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 1e-05
41
- - train_batch_size: 16
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
53
- | 0.1732 | 0.59 | 1000 | 0.1816 | 25.8021 |
54
- | 0.0632 | 1.19 | 2000 | 0.1682 | 31.4649 |
55
- | 0.0535 | 1.78 | 3000 | 0.1571 | 29.6196 |
56
- | 0.021 | 2.38 | 4000 | 0.1654 | 39.7172 |
57
 
58
 
59
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: Rafaelrosendo1/whisper-large-pt
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # whisper-large-pt
17
 
18
+ This model is a fine-tuned version of [Rafaelrosendo1/whisper-large-pt](https://huggingface.co/Rafaelrosendo1/whisper-large-pt) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2592
21
+ - Wer: 23.4359
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 32
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
53
+ | 0.0906 | 1.19 | 1000 | 0.2326 | 24.8668 |
54
+ | 0.0369 | 2.38 | 2000 | 0.2219 | 23.9078 |
55
+ | 0.0136 | 3.57 | 3000 | 0.2426 | 22.2621 |
56
+ | 0.0013 | 4.76 | 4000 | 0.2592 | 23.4359 |
57
 
58
 
59
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-large",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
1
  {
2
+ "_name_or_path": "Rafaelrosendo1/whisper-large-pt",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:101fbc443b835105ffddb36f7e3388eba8dd4a12483c0deeab9551ea04c44ca9
3
  size 6173656065
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c7229f17ecad1f982d396d0b6976842a20697b9b1e498be4c4b0fc5fc985b0
3
  size 6173656065
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7358da30e44f67a06f5811a073a784fd48b3a035ab0f64d6eb9687a0b31bf7b
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732f1257b93d1d4a9bebc119e93e69ad60f18d3b9188bde177ad82fd12926a29
3
  size 4664