End of training
Browse files- README.md +76 -0
- config.json +58 -0
- model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/Feb02_14-36-55_DESKTOP-RI439S7/events.out.tfevents.1706855817.DESKTOP-RI439S7.15196.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- audiofolder
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: pd-diagnosis-model-phonation
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Audio Classification
|
13 |
+
type: audio-classification
|
14 |
+
dataset:
|
15 |
+
name: audiofolder
|
16 |
+
type: audiofolder
|
17 |
+
config: default
|
18 |
+
split: test
|
19 |
+
args: default
|
20 |
+
metrics:
|
21 |
+
- name: Accuracy
|
22 |
+
type: accuracy
|
23 |
+
value: 0.8687258687258688
|
24 |
+
---
|
25 |
+
|
26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
27 |
+
should probably proofread and complete it, then remove this comment. -->
|
28 |
+
|
29 |
+
# pd-diagnosis-model-phonation
|
30 |
+
|
31 |
+
This model was trained from scratch on the audiofolder dataset.
|
32 |
+
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 0.5271
|
34 |
+
- Accuracy: 0.8687
|
35 |
+
|
36 |
+
## Model description
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Intended uses & limitations
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training and evaluation data
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training procedure
|
49 |
+
|
50 |
+
### Training hyperparameters
|
51 |
+
|
52 |
+
The following hyperparameters were used during training:
|
53 |
+
- learning_rate: 2.25e-05
|
54 |
+
- train_batch_size: 4
|
55 |
+
- eval_batch_size: 2
|
56 |
+
- seed: 42
|
57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
+
- lr_scheduler_type: linear
|
59 |
+
- lr_scheduler_warmup_ratio: 0.1
|
60 |
+
- num_epochs: 3
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
+
| 0.2477 | 1.0 | 130 | 1.0240 | 0.7799 |
|
67 |
+
| 0.4452 | 2.0 | 260 | 0.5548 | 0.8533 |
|
68 |
+
| 0.0382 | 3.0 | 390 | 0.5271 | 0.8687 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.37.2
|
74 |
+
- Pytorch 2.1.1
|
75 |
+
- Datasets 2.16.1
|
76 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "C:/Users/ChangRong/.cache/huggingface/whisper-large-v3",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"architectures": [
|
7 |
+
"WhisperForAudioClassification"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"begin_suppress_tokens": [
|
11 |
+
220,
|
12 |
+
50257
|
13 |
+
],
|
14 |
+
"bos_token_id": 50257,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 1280,
|
17 |
+
"decoder_attention_heads": 20,
|
18 |
+
"decoder_ffn_dim": 5120,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 32,
|
21 |
+
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 20,
|
24 |
+
"encoder_ffn_dim": 5120,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 32,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"id2label": {
|
29 |
+
"0": "HC",
|
30 |
+
"1": "PD"
|
31 |
+
},
|
32 |
+
"init_std": 0.02,
|
33 |
+
"is_encoder_decoder": true,
|
34 |
+
"label2id": {
|
35 |
+
"HC": "0",
|
36 |
+
"PD": "1"
|
37 |
+
},
|
38 |
+
"mask_feature_length": 10,
|
39 |
+
"mask_feature_min_masks": 0,
|
40 |
+
"mask_feature_prob": 0.0,
|
41 |
+
"mask_time_length": 10,
|
42 |
+
"mask_time_min_masks": 2,
|
43 |
+
"mask_time_prob": 0.05,
|
44 |
+
"max_length": 448,
|
45 |
+
"max_source_positions": 1500,
|
46 |
+
"max_target_positions": 448,
|
47 |
+
"median_filter_width": 7,
|
48 |
+
"model_type": "whisper",
|
49 |
+
"num_hidden_layers": 32,
|
50 |
+
"num_mel_bins": 128,
|
51 |
+
"pad_token_id": 50256,
|
52 |
+
"scale_embedding": false,
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.37.2",
|
55 |
+
"use_cache": true,
|
56 |
+
"use_weighted_layer_sum": false,
|
57 |
+
"vocab_size": 51866
|
58 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b9b8763d8ab9ee992d9a11d43ab202ba88f54989c754de51d461da923497239
|
3 |
+
size 2549244064
|
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/Feb02_14-36-55_DESKTOP-RI439S7/events.out.tfevents.1706855817.DESKTOP-RI439S7.15196.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ab9769ca613fd6dc325239107524314d763b7bf42c9146e06616009b71f8802
|
3 |
+
size 12733
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd687458cb6ce8d1890fc76845f00d8ff75da8a42874ebb7b89ce1631404f380
|
3 |
+
size 4856
|