End of training
Browse files
README.md
CHANGED
@@ -1,10 +1,70 @@
|
|
1 |
---
|
2 |
-
license: mit
|
3 |
language:
|
4 |
- en
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
---
|
7 |
|
8 |
-
This
|
|
|
9 |
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
2 |
language:
|
3 |
- en
|
4 |
+
license: apache-2.0
|
5 |
+
base_model: openai/whisper-small
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- chris_W/dataset
|
10 |
+
model-index:
|
11 |
+
- name: Whisper-Small-dadirri
|
12 |
+
results: []
|
13 |
---
|
14 |
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
+
# Whisper-Small-dadirri
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the hearing voice dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0231
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 1e-05
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 100
|
48 |
+
- training_steps: 400
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| No log | 0.52 | 50 | 3.0035 |
|
56 |
+
| 4.521 | 1.03 | 100 | 1.4394 |
|
57 |
+
| 4.521 | 1.55 | 150 | 2.7847 |
|
58 |
+
| 1.8786 | 2.06 | 200 | 0.4913 |
|
59 |
+
| 1.8786 | 2.58 | 250 | 0.0458 |
|
60 |
+
| 0.0755 | 3.09 | 300 | 0.0379 |
|
61 |
+
| 0.0755 | 3.61 | 350 | 0.0285 |
|
62 |
+
| 0.0126 | 4.12 | 400 | 0.0231 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.38.0
|
68 |
+
- Pytorch 2.0.1+cu118
|
69 |
+
- Datasets 2.19.1
|
70 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5df77f85f67bb54fdbcf4985dea211c844ae2ea2c5026ac7ed034fb5ee2f4cf8
|
3 |
size 966995080
|
runs/May29_03-24-09_chrisbook-0/events.out.tfevents.1716953051.chrisbook-0.162.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5311321ec6455a64e577c13eddd45746f30f3b5eeec0be175c567ba02f04094f
|
3 |
+
size 9700
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6d5182fd83d701c7a8f3f806ff9b28a3eb66ad5eda18a2e21d3b8ec77688c79
|
3 |
+
size 4603
|