zeon8985army
commited on
Commit
•
7fecaa6
1
Parent(s):
f444820
End of training
Browse files- README.md +88 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/Mar26_03-11-39_03988223b069/events.out.tfevents.1711422700.03988223b069.449.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- id
|
4 |
+
license: apache-2.0
|
5 |
+
library_name: peft
|
6 |
+
tags:
|
7 |
+
- id-asr-leaderboard
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- '-'
|
11 |
+
base_model: openai/whisper-large-v2
|
12 |
+
model-index:
|
13 |
+
- name: /content/zeon8985army/AllIndonesian-fineTunedLargeV2-id-1/checkpoint-192
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# /content/zeon8985army/AllIndonesian-fineTunedLargeV2-id-1/checkpoint-192
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the IndonesianAll dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.2235
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 6e-05
|
44 |
+
- train_batch_size: 16
|
45 |
+
- eval_batch_size: 16
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_steps: 12
|
50 |
+
- training_steps: 276
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 1.7039 | 0.04 | 12 | 1.3824 |
|
58 |
+
| 1.5534 | 0.08 | 24 | 1.1951 |
|
59 |
+
| 1.0896 | 0.12 | 36 | 0.8549 |
|
60 |
+
| 0.8805 | 0.16 | 48 | 0.6975 |
|
61 |
+
| 0.7475 | 0.2 | 60 | 0.6245 |
|
62 |
+
| 0.6436 | 0.25 | 72 | 0.5783 |
|
63 |
+
| 0.606 | 0.29 | 84 | 0.5371 |
|
64 |
+
| 0.5558 | 0.33 | 96 | 0.5013 |
|
65 |
+
| 0.5116 | 0.37 | 108 | 0.4695 |
|
66 |
+
| 0.491 | 0.41 | 120 | 0.4379 |
|
67 |
+
| 0.4481 | 0.45 | 132 | 0.4017 |
|
68 |
+
| 0.4029 | 0.49 | 144 | 0.3533 |
|
69 |
+
| 0.3149 | 0.53 | 156 | 0.2834 |
|
70 |
+
| 0.2592 | 0.57 | 168 | 0.2338 |
|
71 |
+
| 0.2175 | 0.61 | 180 | 0.2311 |
|
72 |
+
| 0.1989 | 0.66 | 192 | 0.2278 |
|
73 |
+
| 0.2031 | 0.7 | 204 | 0.2263 |
|
74 |
+
| 0.2256 | 0.74 | 216 | 0.2250 |
|
75 |
+
| 0.2065 | 0.78 | 228 | 0.2245 |
|
76 |
+
| 0.1916 | 0.82 | 240 | 0.2246 |
|
77 |
+
| 0.2115 | 0.86 | 252 | 0.2242 |
|
78 |
+
| 0.2135 | 0.9 | 264 | 0.2238 |
|
79 |
+
| 0.2177 | 0.94 | 276 | 0.2235 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- PEFT 0.9.0
|
85 |
+
- Transformers 4.38.2
|
86 |
+
- Pytorch 2.2.1+cu121
|
87 |
+
- Datasets 2.18.0
|
88 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-large-v2",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 64,
|
16 |
+
"lora_dropout": 0.1,
|
17 |
+
"megatron_config": null,
|
18 |
+
"megatron_core": "megatron.core",
|
19 |
+
"modules_to_save": null,
|
20 |
+
"peft_type": "LORA",
|
21 |
+
"r": 32,
|
22 |
+
"rank_pattern": {},
|
23 |
+
"revision": null,
|
24 |
+
"target_modules": [
|
25 |
+
"v_proj",
|
26 |
+
"q_proj"
|
27 |
+
],
|
28 |
+
"task_type": null,
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fbe2dd91dcd71d8a6b91f643bbba5e6068c5427e64189753e39c534ff4d8db2
|
3 |
+
size 62969640
|
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/Mar26_03-11-39_03988223b069/events.out.tfevents.1711422700.03988223b069.449.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c59a0c78a6012d0c993acc646c7757dc45fbfe53b42b8613118012d6e1dacd85
|
3 |
+
size 17299
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3fd78c151565ca4560c33bd3021a2bedd5dc735b3861a8431dc4d7788f736cb
|
3 |
+
size 5112
|