End of training
Browse files- README.md +92 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/May29_13-21-37_a100gpu3/events.out.tfevents.1716981721.a100gpu3.3419786.0 +3 -0
- runs/May29_13-35-43_a100gpu3/events.out.tfevents.1716982555.a100gpu3.3419786.1 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: openai/whisper-small
|
7 |
+
datasets:
|
8 |
+
- librispeech
|
9 |
+
model-index:
|
10 |
+
- name: Whisper Small English 1h
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# Whisper Small English 1h
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the librispeech dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.1760
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 50
|
47 |
+
- num_epochs: 30
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 1.7144 | 1.0 | 39 | 1.4900 |
|
55 |
+
| 0.4793 | 2.0 | 78 | 0.5925 |
|
56 |
+
| 0.3478 | 3.0 | 117 | 0.5148 |
|
57 |
+
| 0.2552 | 4.0 | 156 | 0.4314 |
|
58 |
+
| 0.1964 | 5.0 | 195 | 0.1524 |
|
59 |
+
| 0.0281 | 6.0 | 234 | 0.1534 |
|
60 |
+
| 0.0254 | 7.0 | 273 | 0.1537 |
|
61 |
+
| 0.0133 | 8.0 | 312 | 0.1613 |
|
62 |
+
| 0.011 | 9.0 | 351 | 0.1601 |
|
63 |
+
| 0.0088 | 10.0 | 390 | 0.1619 |
|
64 |
+
| 0.007 | 11.0 | 429 | 0.1659 |
|
65 |
+
| 0.0067 | 12.0 | 468 | 0.1647 |
|
66 |
+
| 0.0056 | 13.0 | 507 | 0.1671 |
|
67 |
+
| 0.0053 | 14.0 | 546 | 0.1683 |
|
68 |
+
| 0.0047 | 15.0 | 585 | 0.1687 |
|
69 |
+
| 0.0041 | 16.0 | 624 | 0.1703 |
|
70 |
+
| 0.0037 | 17.0 | 663 | 0.1715 |
|
71 |
+
| 0.0037 | 18.0 | 702 | 0.1721 |
|
72 |
+
| 0.0035 | 19.0 | 741 | 0.1726 |
|
73 |
+
| 0.0034 | 20.0 | 780 | 0.1730 |
|
74 |
+
| 0.0032 | 21.0 | 819 | 0.1738 |
|
75 |
+
| 0.0031 | 22.0 | 858 | 0.1741 |
|
76 |
+
| 0.0033 | 23.0 | 897 | 0.1744 |
|
77 |
+
| 0.003 | 24.0 | 936 | 0.1748 |
|
78 |
+
| 0.0029 | 25.0 | 975 | 0.1756 |
|
79 |
+
| 0.003 | 26.0 | 1014 | 0.1756 |
|
80 |
+
| 0.0028 | 27.0 | 1053 | 0.1756 |
|
81 |
+
| 0.0027 | 28.0 | 1092 | 0.1760 |
|
82 |
+
| 0.0027 | 29.0 | 1131 | 0.1760 |
|
83 |
+
| 0.0027 | 30.0 | 1170 | 0.1760 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- PEFT 0.10.0
|
89 |
+
- Transformers 4.40.1
|
90 |
+
- Pytorch 2.3.0+cu121
|
91 |
+
- Datasets 2.19.0
|
92 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "openai/whisper-small",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 64,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"q_proj"
|
28 |
+
],
|
29 |
+
"task_type": null,
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a2a60e64d95f04e1c46c60820d5745bce1514bd94983d2e4e7949b8bed05607
|
3 |
+
size 14176064
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 80,
|
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/May29_13-21-37_a100gpu3/events.out.tfevents.1716981721.a100gpu3.3419786.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:880ade6b9927a915583f5e6b0e07e2fc7291e3eba994adb6504932b35fb31325
|
3 |
+
size 7576
|
runs/May29_13-35-43_a100gpu3/events.out.tfevents.1716982555.a100gpu3.3419786.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bb8f66f29a3cb22cf5b3d34efcb4cb20d701d80e34d6ff2d558c59e657a1128
|
3 |
+
size 23688
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b88638d015a9d74d0c63d8add54001fcfe0778d30fc924530b74822b951ebc7f
|
3 |
+
size 5176
|