Hugging Face's logo

MathildeB3
/
checkpoints

PEFT
Safetensors
Transformers
French
lora
Model card Files
xet
Community
MathildeB3 commited on
Commit
7bab250
·
verified ·
1 Parent(s): f5a996c

End of training

Browse files
Files changed (4) hide show
  1. README.md +8 -8
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -22,8 +22,8 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the FullDatabase dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.6805
26
- - Wer: 0.3365
27
 
28
  ## Model description
29
 
@@ -55,12 +55,12 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:------:|:----:|:---------------:|:------:|
58
- | 2.7049 | 0.4762 | 20 | 2.4821 | 0.4627 |
59
- | 1.3583 | 0.9524 | 40 | 1.3041 | 0.3862 |
60
- | 1.2276 | 1.4286 | 60 | 0.9667 | 0.3958 |
61
- | 0.6298 | 1.9048 | 80 | 0.7598 | 0.3537 |
62
- | 0.945 | 2.3810 | 100 | 0.7089 | 0.3537 |
63
- | 0.3522 | 2.8571 | 120 | 0.6805 | 0.3365 |
64
 
65
 
66
  ### Framework versions
 
22
 
23
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the FullDatabase dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 0.6571
26
+ - Wer: 0.3250
27
 
28
  ## Model description
29
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:------:|:----:|:---------------:|:------:|
58
+ | 1.3351 | 0.4762 | 20 | 1.4084 | 0.3556 |
59
+ | 1.2002 | 0.9524 | 40 | 1.1677 | 0.4723 |
60
+ | 0.8027 | 1.4286 | 60 | 0.7820 | 0.3308 |
61
+ | 0.486 | 1.9048 | 80 | 0.6790 | 0.4857 |
62
+ | 0.535 | 2.3810 | 100 | 0.6774 | 0.3327 |
63
+ | 0.2083 | 2.8571 | 120 | 0.6571 | 0.3250 |
64
 
65
 
66
  ### Framework versions
adapter_config.json CHANGED
@@ -32,8 +32,8 @@
32
  "rank_pattern": {},
33
  "revision": null,
34
  "target_modules": [
35
- "v_proj",
36
- "q_proj"
37
  ],
38
  "target_parameters": null,
39
  "task_type": null,
 
32
  "rank_pattern": {},
33
  "revision": null,
34
  "target_modules": [
35
+ "q_proj",
36
+ "v_proj"
37
  ],
38
  "target_parameters": null,
39
  "task_type": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd31e90c13829cde6bcae9292e391e761c726af3776cb60a20671b2c43ce071d
3
  size 14176064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eda5b90c697c10821a1d3d1c03b52a88e04af553663537513f9953f2ad62e91
3
  size 14176064
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ff4b685165405bac744de0753778ea09d8b28cb413be3af62d8886e3d7c1b6a
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be969276afdc928f4edc44a13a22d219ad95ec89f09045ec7aa31e81ca6947a1
3
  size 5969