Hugging Face's logo

miosipof
/
asr2_medium_CRSPR_v0.5

PEFT
TensorBoard
Safetensors
Italian
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
miosipof commited on
Commit
b6905ba
·
verified ·
1 Parent(s): 0e96838

End of training

Browse files
Files changed (15) hide show
  1. README.md +92 -0
  2. adapter_config.json +36 -0
  3. adapter_model.safetensors +3 -0
  4. preprocessor_config.json +14 -0
  5. runs/Feb13_08-37-21_e7511933f02a/events.out.tfevents.1739435845.e7511933f02a +3 -0
  6. runs/Feb13_08-45-11_e7511933f02a/events.out.tfevents.1739436316.e7511933f02a +3 -0
  7. runs/Feb13_08-51-06_e7511933f02a/events.out.tfevents.1739436670.e7511933f02a +3 -0
  8. runs/Feb13_08-52-53_e7511933f02a/events.out.tfevents.1739436781.e7511933f02a +3 -0
  9. runs/Feb13_08-54-29_e7511933f02a/events.out.tfevents.1739436873.e7511933f02a +3 -0
  10. runs/Feb13_09-18-39_e7511933f02a/events.out.tfevents.1739438322.e7511933f02a +3 -0
  11. runs/Feb13_09-24-19_e7511933f02a/events.out.tfevents.1739438664.e7511933f02a +3 -0
  12. runs/Feb13_18-18-08_e7511933f02a/events.out.tfevents.1739470691.e7511933f02a +3 -0
  13. runs/Feb13_18-19-05_e7511933f02a/events.out.tfevents.1739470747.e7511933f02a +3 -0
  14. runs/Feb13_19-11-55_e7511933f02a/events.out.tfevents.1739473928.e7511933f02a +3 -0
  15. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ language:
4
+ - it
5
+ license: cc-by-nc-4.0
6
+ base_model: nyrahealth/CrisperWhisper
7
+ tags:
8
+ - generated_from_trainer
9
+ datasets:
10
+ - b-brave-clean
11
+ metrics:
12
+ - wer
13
+ model-index:
14
+ - name: Whisper-Crisper
15
+ results:
16
+ - task:
17
+ type: automatic-speech-recognition
18
+ name: Automatic Speech Recognition
19
+ dataset:
20
+ name: b-brave-clean
21
+ type: b-brave-clean
22
+ config: default
23
+ split: test
24
+ args: default
25
+ metrics:
26
+ - type: wer
27
+ value: 155.63816604708796
28
+ name: Wer
29
+ ---
30
+
31
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
+ should probably proofread and complete it, then remove this comment. -->
33
+
34
+ # Whisper-Crisper
35
+
36
+ This model is a fine-tuned version of [nyrahealth/CrisperWhisper](https://huggingface.co/nyrahealth/CrisperWhisper) on the b-brave-clean dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.2971
39
+ - Wer: 155.6382
40
+ - Cer: 74.4218
41
+ - Lr: 0.0000
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 0.0003
61
+ - train_batch_size: 4
62
+ - eval_batch_size: 4
63
+ - seed: 42
64
+ - gradient_accumulation_steps: 2
65
+ - total_train_batch_size: 8
66
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
67
+ - lr_scheduler_type: linear
68
+ - lr_scheduler_warmup_ratio: 0.5
69
+ - num_epochs: 8
70
+ - mixed_precision_training: Native AMP
71
+
72
+ ### Training results
73
+
74
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Lr |
75
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:--------:|:------:|
76
+ | 1.0227 | 1.0 | 335 | 0.8979 | 601.9827 | 363.8095 | 0.0001 |
77
+ | 0.5552 | 2.0 | 670 | 0.5294 | 1520.4461 | 678.7302 | 0.0002 |
78
+ | 0.4207 | 3.0 | 1005 | 0.4611 | 403.5936 | 219.1610 | 0.0002 |
79
+ | 0.2025 | 4.0 | 1340 | 0.3812 | 346.8401 | 162.0408 | 0.0003 |
80
+ | 0.1216 | 5.0 | 1675 | 0.3001 | 400.3717 | 203.6054 | 0.0002 |
81
+ | 0.0478 | 6.0 | 2010 | 0.2932 | 198.6369 | 94.8299 | 0.0001 |
82
+ | 0.0313 | 7.0 | 2345 | 0.3033 | 241.0161 | 115.3288 | 0.0001 |
83
+ | 0.012 | 7.9776 | 2672 | 0.2971 | 155.6382 | 74.4218 | 0.0000 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - PEFT 0.14.0
89
+ - Transformers 4.48.3
90
+ - Pytorch 2.2.0
91
+ - Datasets 3.2.0
92
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "WhisperForConditionalGeneration",
5
+ "parent_library": "transformers.models.whisper.modeling_whisper"
6
+ },
7
+ "base_model_name_or_path": "nyrahealth/CrisperWhisper",
8
+ "bias": "none",
9
+ "eva_config": null,
10
+ "exclude_modules": null,
11
+ "fan_in_fan_out": false,
12
+ "inference_mode": true,
13
+ "init_lora_weights": true,
14
+ "layer_replication": null,
15
+ "layers_pattern": null,
16
+ "layers_to_transform": null,
17
+ "loftq_config": {},
18
+ "lora_alpha": 32,
19
+ "lora_bias": false,
20
+ "lora_dropout": 0.1,
21
+ "megatron_config": null,
22
+ "megatron_core": "megatron.core",
23
+ "modules_to_save": null,
24
+ "peft_type": "LORA",
25
+ "r": 16,
26
+ "rank_pattern": {},
27
+ "revision": null,
28
+ "target_modules": [
29
+ "q_proj",
30
+ "v_proj",
31
+ "k_proj"
32
+ ],
33
+ "task_type": null,
34
+ "use_dora": false,
35
+ "use_rslora": false
36
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eac06397f3cfd50bd813fea0e1a4c2a37ba2842c441885d599f1f463c92873a
3
+ size 47268448
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
runs/Feb13_08-37-21_e7511933f02a/events.out.tfevents.1739435845.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0197d488fe45f7e179ab63a871b8db58c454747e162015b739efcf1e37d7d8d4
3
+ size 6844
runs/Feb13_08-45-11_e7511933f02a/events.out.tfevents.1739436316.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa2b4357ae49f6fe26568cda0b1c35bde6ea99b6316ef97c7c6ce0c317261ca
3
+ size 5812
runs/Feb13_08-51-06_e7511933f02a/events.out.tfevents.1739436670.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096ef24636654dd62ad4387b5b7e5a2b042f184bbcaea1b7f196ece7dda8f671
3
+ size 5812
runs/Feb13_08-52-53_e7511933f02a/events.out.tfevents.1739436781.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03244467f637fc710e840de6e211ed24da96dd2e0c9c30feaf3142d0bf3f3db6
3
+ size 5810
runs/Feb13_08-54-29_e7511933f02a/events.out.tfevents.1739436873.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1a9100fde5d51801003bb7256c703df8b8ebda3261d94093f1fcc81e56fc69
3
+ size 8533
runs/Feb13_09-18-39_e7511933f02a/events.out.tfevents.1739438322.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0af24958104c0f9c08e42037992c51c91089376ee7d677e686db327a5fcee31
3
+ size 5810
runs/Feb13_09-24-19_e7511933f02a/events.out.tfevents.1739438664.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3597e827de948ce75bec4a9e0ffd956ec9e0e105d135d9b2a7dd58bd2174583d
3
+ size 12731
runs/Feb13_18-18-08_e7511933f02a/events.out.tfevents.1739470691.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c260a904c703b19fbe17d97374c8aa592fea53764efb7169e131509abfe2eee
3
+ size 5810
runs/Feb13_18-19-05_e7511933f02a/events.out.tfevents.1739470747.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e3e8f0b5b2c6926f8ba42137a085a841b023a513e7cd6013d9cfdceb9d0b11
3
+ size 12098
runs/Feb13_19-11-55_e7511933f02a/events.out.tfevents.1739473928.e7511933f02a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58d13628818408019edc86f9a1b5ac7cb052eb92f6a879d18b6b168fb4191e2
3
+ size 31799
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c47319a1d47f0817d8cbceb42164447fa0de2b15c4e0d4d182cfcf2ccc48a3
3
+ size 5496