End of training
Browse files- README.md +74 -0
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
language:
|
4 |
+
- multilingual
|
5 |
+
license: apache-2.0
|
6 |
+
base_model: openai/whisper-large-v2
|
7 |
+
tags:
|
8 |
+
- whisper-event
|
9 |
+
- generated_from_trainer
|
10 |
+
metrics:
|
11 |
+
- wer
|
12 |
+
model-index:
|
13 |
+
- name: Fauna-v0.7 - Rootflo
|
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 |
+
# Fauna-v0.7 - Rootflo
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on an unknown dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.0558
|
25 |
+
- Wer: 60.7190
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 1e-06
|
45 |
+
- train_batch_size: 72
|
46 |
+
- eval_batch_size: 96
|
47 |
+
- seed: 42
|
48 |
+
- distributed_type: multi-GPU
|
49 |
+
- num_devices: 4
|
50 |
+
- gradient_accumulation_steps: 2
|
51 |
+
- total_train_batch_size: 576
|
52 |
+
- total_eval_batch_size: 384
|
53 |
+
- optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
54 |
+
- lr_scheduler_type: cosine
|
55 |
+
- lr_scheduler_warmup_steps: 1500
|
56 |
+
- training_steps: 5000
|
57 |
+
- mixed_precision_training: Native AMP
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
62 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
63 |
+
| 0.0301 | 1.0695 | 500 | 0.0498 | 58.1393 |
|
64 |
+
| 0.0278 | 2.1390 | 1000 | 0.0515 | 58.0461 |
|
65 |
+
| 0.0261 | 3.2086 | 1500 | 0.0538 | 59.1088 |
|
66 |
+
| 0.0241 | 4.2781 | 2000 | 0.0558 | 60.7190 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.46.1
|
72 |
+
- Pytorch 2.5.1+cu124
|
73 |
+
- Datasets 3.0.2
|
74 |
+
- Tokenizers 0.20.3
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4992706480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f7f5ae7bc3e965948b7989cd4d16a6327fa91ab2540996e4439c9963ecf3985
|
3 |
size 4992706480
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:195c1868dfcb9f2f23ace354f61cec7bafb54f388d73954b8adc1c59f4a0146d
|
3 |
size 1180663192
|