End of training
Browse files
README.md
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
language:
|
4 |
+
- fa
|
5 |
+
license: mit
|
6 |
+
base_model: openai/whisper-large-v3-turbo
|
7 |
+
tags:
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- mozilla-foundation/common_voice_17_0
|
11 |
+
metrics:
|
12 |
+
- wer
|
13 |
+
model-index:
|
14 |
+
- name: Whisper-large-v3-turbo-fa - Sadegh Karimi
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Automatic Speech Recognition
|
18 |
+
type: automatic-speech-recognition
|
19 |
+
dataset:
|
20 |
+
name: Common Voice 17.0
|
21 |
+
type: mozilla-foundation/common_voice_17_0
|
22 |
+
config: fa
|
23 |
+
split: test
|
24 |
+
args: 'config: hi, split: test'
|
25 |
+
metrics:
|
26 |
+
- name: Wer
|
27 |
+
type: wer
|
28 |
+
value: 9.627528266117483
|
29 |
+
---
|
30 |
+
|
31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
+
should probably proofread and complete it, then remove this comment. -->
|
33 |
+
|
34 |
+
# Whisper-large-v3-turbo-fa - Sadegh Karimi
|
35 |
+
|
36 |
+
This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the Common Voice 17.0 dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.0839
|
39 |
+
- Wer: 9.6275
|
40 |
+
|
41 |
+
## Model description
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Intended uses & limitations
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training and evaluation data
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Training procedure
|
54 |
+
|
55 |
+
### Training hyperparameters
|
56 |
+
|
57 |
+
The following hyperparameters were used during training:
|
58 |
+
- learning_rate: 1e-05
|
59 |
+
- train_batch_size: 16
|
60 |
+
- eval_batch_size: 8
|
61 |
+
- seed: 42
|
62 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
63 |
+
- lr_scheduler_type: linear
|
64 |
+
- lr_scheduler_warmup_steps: 500
|
65 |
+
- training_steps: 10000
|
66 |
+
- mixed_precision_training: Native AMP
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
71 |
+
|:-------------:|:------:|:-----:|:---------------:|:-------:|
|
72 |
+
| 0.1789 | 0.0217 | 500 | 0.2427 | 26.4099 |
|
73 |
+
| 0.2077 | 0.0435 | 1000 | 0.2296 | 27.1873 |
|
74 |
+
| 0.1928 | 0.0652 | 1500 | 0.2320 | 27.5951 |
|
75 |
+
| 0.1801 | 0.0869 | 2000 | 0.2026 | 24.0409 |
|
76 |
+
| 0.1865 | 0.1086 | 2500 | 0.1925 | 22.3742 |
|
77 |
+
| 0.1535 | 0.1304 | 3000 | 0.1872 | 22.9511 |
|
78 |
+
| 0.1463 | 0.1521 | 3500 | 0.1786 | 21.5436 |
|
79 |
+
| 0.0935 | 0.1738 | 4000 | 0.1749 | 20.5330 |
|
80 |
+
| 0.1052 | 0.1956 | 4500 | 0.1597 | 19.0314 |
|
81 |
+
| 0.091 | 0.2173 | 5000 | 0.1553 | 20.2125 |
|
82 |
+
| 0.0743 | 0.2390 | 5500 | 0.1474 | 16.9160 |
|
83 |
+
| 0.096 | 0.2607 | 6000 | 0.1352 | 15.9027 |
|
84 |
+
| 0.111 | 0.2825 | 6500 | 0.1259 | 14.9071 |
|
85 |
+
| 0.089 | 0.3042 | 7000 | 0.1179 | 14.1146 |
|
86 |
+
| 0.0813 | 0.3259 | 7500 | 0.1101 | 12.8653 |
|
87 |
+
| 0.072 | 0.3477 | 8000 | 0.1012 | 11.8138 |
|
88 |
+
| 0.0715 | 0.3694 | 8500 | 0.0948 | 10.9791 |
|
89 |
+
| 0.0683 | 0.3911 | 9000 | 0.0903 | 10.2563 |
|
90 |
+
| 0.0634 | 0.4128 | 9500 | 0.0861 | 9.6616 |
|
91 |
+
| 0.0739 | 0.4346 | 10000 | 0.0839 | 9.6275 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- Transformers 4.47.1
|
97 |
+
- Pytorch 2.1.0+cu118
|
98 |
+
- Datasets 3.2.0
|
99 |
+
- Tokenizers 0.21.0
|
generation_config.json
CHANGED
@@ -245,5 +245,5 @@
|
|
245 |
"transcribe": 50360,
|
246 |
"translate": 50359
|
247 |
},
|
248 |
-
"transformers_version": "4.
|
249 |
}
|
|
|
245 |
"transcribe": 50360,
|
246 |
"translate": 50359
|
247 |
},
|
248 |
+
"transformers_version": "4.47.1"
|
249 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3235581408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4684c622f9ed7cca96a0694cb277a58f912d2550382c53e920d48141d3bca1b1
|
3 |
size 3235581408
|
runs/Jan10_17-02-24_20c86341c6b2/events.out.tfevents.1736528576.20c86341c6b2.1373.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dab2e35fb2bd1ad52bf557201ae38a83ef97e6b3da48c766d2736f7f8f2490f1
|
3 |
+
size 83331
|