Hugging Face's logo

miosipof
/
whisper_medium_BB_and_EC_v2.2

PEFT
Safetensors
Italian
Generated from Trainer
Eval Results
Model card Files Community
miosipof commited on
Commit
a561eb5
·
verified ·
1 Parent(s): 68f50bb

End of training

Browse files
Files changed (4) hide show
  1. README.md +9 -7
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  args: default
24
  metrics:
25
  - type: wer
26
- value: 47.95539033457249
27
  name: Wer
28
  ---
29
 
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  This model is a fine-tuned version of [b-brave/asr_double_training_15-10-2024_merged](https://huggingface.co/b-brave/asr_double_training_15-10-2024_merged) on the ASR_BB_and_EC dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.3965
38
- - Wer: 47.9554
39
 
40
  ## Model description
41
 
@@ -63,16 +63,18 @@ The following hyperparameters were used during training:
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: constant
65
  - lr_scheduler_warmup_steps: 50
66
- - num_epochs: 3
67
  - mixed_precision_training: Native AMP
68
 
69
  ### Training results
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer |
72
  |:-------------:|:------:|:----:|:---------------:|:-------:|
73
- | 0.6316 | 0.8929 | 100 | 0.4368 | 37.1747 |
74
- | 0.4745 | 1.7857 | 200 | 0.4086 | 48.6989 |
75
- | 0.4211 | 2.6786 | 300 | 0.3965 | 47.9554 |
 
 
76
 
77
 
78
  ### Framework versions
 
23
  args: default
24
  metrics:
25
  - type: wer
26
+ value: 39.03345724907063
27
  name: Wer
28
  ---
29
 
 
34
 
35
  This model is a fine-tuned version of [b-brave/asr_double_training_15-10-2024_merged](https://huggingface.co/b-brave/asr_double_training_15-10-2024_merged) on the ASR_BB_and_EC dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.3711
38
+ - Wer: 39.0335
39
 
40
  ## Model description
41
 
 
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: constant
65
  - lr_scheduler_warmup_steps: 50
66
+ - num_epochs: 5
67
  - mixed_precision_training: Native AMP
68
 
69
  ### Training results
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer |
72
  |:-------------:|:------:|:----:|:---------------:|:-------:|
73
+ | 0.5871 | 0.8929 | 100 | 0.4197 | 64.5601 |
74
+ | 0.4071 | 1.7857 | 200 | 0.3965 | 47.5836 |
75
+ | 0.3503 | 2.6786 | 300 | 0.3837 | 46.5923 |
76
+ | 0.2778 | 3.5714 | 400 | 0.3777 | 46.2206 |
77
+ | 0.2195 | 4.4643 | 500 | 0.3711 | 39.0335 |
78
 
79
 
80
  ### Framework versions
adapter_config.json CHANGED
@@ -13,7 +13,7 @@
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
- "lora_alpha": 32,
17
  "lora_dropout": 0.01,
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
 
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
+ "lora_alpha": 64,
17
  "lora_dropout": 0.01,
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bed9aedf4567784db6f5be218dea51883b22c36fe559f645eb3e3048a87c197d
3
  size 37789960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ea3bb76f00b5c9572fa7d6a46d97acf06f30d4072b5334b08b7931c45c4d60
3
  size 37789960
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e38cca5d1e211828e034e2b518002731563038434ea35002737f016bc0385a69
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74f173f5d8a8747d397daf447cd1cdc6705eeb46951c58adcc17396241a6bc5
3
  size 5368