Hugging Face's logo

giigii91
/
whisper-tiny_v2.1-ro

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Romanian
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
giigii91 commited on
Commit
d1ebce3
•
1 Parent(s): cbac137

Model save

Browse files
Files changed (4) hide show
  1. README.md +8 -6
  2. config.json +2 -2
  3. model.safetensors +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-tiny
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # whisper-tiny_v2.1-ro
17
 
18
- This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_11_0 dataset.
19
 
20
  ## Model description
21
 
@@ -35,12 +35,14 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 1e-05
38
- - train_batch_size: 128
39
- - eval_batch_size: 128
40
  - seed: 42
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
- - lr_scheduler_type: cosine_with_restarts
43
- - lr_scheduler_warmup_steps: 500
44
  - training_steps: 5000
45
  - mixed_precision_training: Native AMP
46
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: giigii91/whisper-tiny_v2.2-ro
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
15
 
16
  # whisper-tiny_v2.1-ro
17
 
18
+ This model is a fine-tuned version of [giigii91/whisper-tiny_v2.2-ro](https://huggingface.co/giigii91/whisper-tiny_v2.2-ro) on the common_voice_11_0 dataset.
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 1e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 8
40
  - seed: 42
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 32
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 100
46
  - training_steps: 5000
47
  - mixed_precision_training: Native AMP
48
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-tiny",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
@@ -19,7 +19,7 @@
19
  "decoder_layerdrop": 0.0,
20
  "decoder_layers": 4,
21
  "decoder_start_token_id": 50258,
22
- "dropout": 0.01,
23
  "encoder_attention_heads": 6,
24
  "encoder_ffn_dim": 1536,
25
  "encoder_layerdrop": 0.0,
 
1
  {
2
+ "_name_or_path": "giigii91/whisper-tiny_v2.2-ro",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
19
  "decoder_layerdrop": 0.0,
20
  "decoder_layers": 4,
21
  "decoder_start_token_id": 50258,
22
+ "dropout": 0.2,
23
  "encoder_attention_heads": 6,
24
  "encoder_ffn_dim": 1536,
25
  "encoder_layerdrop": 0.0,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b122d8d9123b9608b89e1366c95d67313dfa1f446a52c34117f2620f566319a
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c674250c0627ee0c3bd006f4a245073ccd3751e0e87b3e7f8da160a1af00e45
3
  size 151061672
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:288e9271ac6b1d94545071413bdbe058d059dad28cf5312f54092517e4304460
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b56b74820e0bcb15ab866da98c0564397e9f1679c07ece8b4edbe36e45a8ec
3
  size 5240