End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: openai/whisper-medium.en
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: medium_cross.en
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# medium_cross.en
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7616
|
| 22 |
+
- Wer: 34.6503
|
| 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 10
|
| 48 |
+
- training_steps: 401
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 55 |
+
| 2.2838 | 0.5155 | 200 | 1.0021 | 36.0184 |
|
| 56 |
+
| 0.9275 | 1.0309 | 400 | 0.7616 | 34.6503 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- Transformers 4.49.0.dev0
|
| 62 |
+
- Pytorch 2.5.1+cu124
|
| 63 |
+
- Datasets 3.2.0
|
| 64 |
+
- Tokenizers 0.21.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
11,
|
| 5 |
+
4
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
14,
|
| 9 |
+
1
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
14,
|
| 13 |
+
12
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
14,
|
| 17 |
+
14
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
15,
|
| 21 |
+
4
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
16,
|
| 25 |
+
0
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
16,
|
| 29 |
+
4
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
16,
|
| 33 |
+
9
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
17,
|
| 37 |
+
12
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
17,
|
| 41 |
+
14
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
18,
|
| 45 |
+
7
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
18,
|
| 49 |
+
10
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
18,
|
| 53 |
+
15
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
20,
|
| 57 |
+
0
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
20,
|
| 61 |
+
3
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
20,
|
| 65 |
+
9
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
20,
|
| 69 |
+
14
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
21,
|
| 73 |
+
12
|
| 74 |
+
]
|
| 75 |
+
],
|
| 76 |
+
"begin_suppress_tokens": [
|
| 77 |
+
220,
|
| 78 |
+
50256
|
| 79 |
+
],
|
| 80 |
+
"bos_token_id": 50257,
|
| 81 |
+
"decoder_start_token_id": 50257,
|
| 82 |
+
"eos_token_id": 50256,
|
| 83 |
+
"forced_decoder_ids": [
|
| 84 |
+
[
|
| 85 |
+
1,
|
| 86 |
+
50362
|
| 87 |
+
]
|
| 88 |
+
],
|
| 89 |
+
"is_multilingual": false,
|
| 90 |
+
"max_initial_timestamp_index": 50,
|
| 91 |
+
"max_length": 448,
|
| 92 |
+
"no_timestamps_token_id": 50362,
|
| 93 |
+
"pad_token_id": 50256,
|
| 94 |
+
"prev_sot_token_id": 50360,
|
| 95 |
+
"return_timestamps": false,
|
| 96 |
+
"suppress_tokens": [],
|
| 97 |
+
"transformers_version": "4.49.0.dev0"
|
| 98 |
+
}
|
runs/Feb10_14-18-43_2c97a6736ff0/events.out.tfevents.1739197140.2c97a6736ff0.469.0
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:abbb08903a4a935dbadee8dcecfb3c464ad39407920191246e41800a39911e77
|
| 3 |
+
size 7328
|