Hugging Face's logo

emonidi
/
whisper-medium-order

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
emonidi commited on
Commit
8d2e25f
·
1 Parent(s): f6bc90a

emonidi/whisper-tiny-order

Browse files
Files changed (6) hide show
  1. README.md +15 -15
  2. config.json +9 -9
  3. generation_config.json +1 -2
  4. model.safetensors +2 -2
  5. runs/Dec22_13-12-36_3c13ff75796d/events.out.tfevents.1703250763.3c13ff75796d.6177.0 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: shripadbhat/whisper-medium-bg
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # whisper-medium-order
17
 
18
- This model is a fine-tuned version of [shripadbhat/whisper-medium-bg](https://huggingface.co/shripadbhat/whisper-medium-bg) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0001
21
  - Wer: 0.0
22
 
23
  ## Model description
@@ -50,18 +50,18 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 0.0008 | 3.0 | 5 | 0.0541 | 2.2222 |
56
- | 0.0002 | 6.0 | 10 | 0.0016 | 0.0 |
57
- | 0.0001 | 9.0 | 15 | 0.0003 | 0.0 |
58
- | 0.0001 | 12.0 | 20 | 0.0002 | 0.0 |
59
- | 0.0001 | 15.0 | 25 | 0.0001 | 0.0 |
60
- | 0.0001 | 18.0 | 30 | 0.0001 | 0.0 |
61
- | 0.0001 | 21.0 | 35 | 0.0001 | 0.0 |
62
- | 0.0001 | 24.0 | 40 | 0.0001 | 0.0 |
63
- | 0.0001 | 27.0 | 45 | 0.0001 | 0.0 |
64
- | 0.0001 | 29.87 | 50 | 0.0001 | 0.0 |
65
 
66
 
67
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: nandovallec/whisper-tiny-bg-l
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # whisper-medium-order
17
 
18
+ This model is a fine-tuned version of [nandovallec/whisper-tiny-bg-l](https://huggingface.co/nandovallec/whisper-tiny-bg-l) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0173
21
  - Wer: 0.0
22
 
23
  ## Model description
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 0.624 | 3.0 | 5 | 1.4084 | 111.7647 |
56
+ | 0.5102 | 6.0 | 10 | 0.5733 | 43.1373 |
57
+ | 0.2173 | 8.78 | 15 | 0.3225 | 31.3725 |
58
+ | 0.0178 | 11.29 | 20 | 0.2035 | 27.4510 |
59
+ | 0.0138 | 14.0 | 25 | 0.1143 | 21.5686 |
60
+ | 0.036 | 17.0 | 30 | 0.0603 | 3.9216 |
61
+ | 0.0296 | 20.0 | 35 | 0.0366 | 1.9608 |
62
+ | 0.0074 | 22.59 | 40 | 0.0250 | 1.9608 |
63
+ | 0.0014 | 25.1 | 45 | 0.0191 | 0.0 |
64
+ | 0.0051 | 28.0 | 50 | 0.0173 | 0.0 |
65
 
66
 
67
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "shripadbhat/whisper-medium-bg",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
@@ -13,17 +13,17 @@
13
  ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
16
- "d_model": 1024,
17
- "decoder_attention_heads": 16,
18
- "decoder_ffn_dim": 4096,
19
  "decoder_layerdrop": 0.0,
20
- "decoder_layers": 24,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
- "encoder_attention_heads": 16,
24
- "encoder_ffn_dim": 4096,
25
  "encoder_layerdrop": 0.0,
26
- "encoder_layers": 24,
27
  "eos_token_id": 50257,
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
@@ -39,7 +39,7 @@
39
  "max_target_positions": 448,
40
  "median_filter_width": 7,
41
  "model_type": "whisper",
42
- "num_hidden_layers": 24,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
 
1
  {
2
+ "_name_or_path": "nandovallec/whisper-tiny-bg-l",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
13
  ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
16
+ "d_model": 384,
17
+ "decoder_attention_heads": 6,
18
+ "decoder_ffn_dim": 1536,
19
  "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 4,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
+ "encoder_attention_heads": 6,
24
+ "encoder_ffn_dim": 1536,
25
  "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 4,
27
  "eos_token_id": 50257,
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
 
39
  "max_target_positions": 448,
40
  "median_filter_width": 7,
41
  "model_type": "whisper",
42
+ "num_hidden_layers": 4,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
generation_config.json CHANGED
@@ -10,6 +10,5 @@
10
  "pad_token_id": 50257,
11
  "return_timestamps": false,
12
  "suppress_tokens": [],
13
- "transformers_version": "4.35.2",
14
- "use_cache": false
15
  }
 
10
  "pad_token_id": 50257,
11
  "return_timestamps": false,
12
  "suppress_tokens": [],
13
+ "transformers_version": "4.35.2"
 
14
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40b88c0a048812c9385d26a4aed4468f1805b26bc6f225c9050ccb47591fa8e0
3
- size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25c2a841f3d1203bdf1ad1a76e2c88eacde13715d58bb05f7a0bd30781257ca
3
+ size 151061672
runs/Dec22_13-12-36_3c13ff75796d/events.out.tfevents.1703250763.3c13ff75796d.6177.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13c0667aead59b1254798f31ace6aa2a304408eaf12838c3a48b74304f97045
3
+ size 16217
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e7120454040ac52ff976b0096c6023c69a095f4b8de81589d7c5d6249d2adc3
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806ac3f1519af37cb704bdd091c514f887a1628b949997f0e614b0ce80eb8c0b
3
  size 4728