Model save
Browse files
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
metrics:
|
@@ -13,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# whisper-tiny-hi2_test
|
15 |
|
16 |
-
This model
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
-
- Wer:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,12 +37,13 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- learning_rate:
|
39 |
- train_batch_size: 32
|
40 |
- eval_batch_size: 1
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
-
- lr_scheduler_type:
|
|
|
44 |
- training_steps: 200
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
@@ -48,11 +51,11 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
51 |
-
|
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: openai/whisper-tiny
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
15 |
|
16 |
# whisper-tiny-hi2_test
|
17 |
|
18 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.5504
|
21 |
+
- Wer: 63.9035
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 3.75e-05
|
41 |
- train_batch_size: 32
|
42 |
- eval_batch_size: 1
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: constant
|
46 |
+
- lr_scheduler_warmup_steps: 50
|
47 |
- training_steps: 200
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
54 |
+
| 0.6803 | 1.25 | 40 | 0.6102 | 65.9441 |
|
55 |
+
| 0.3649 | 2.5 | 80 | 0.5037 | 58.3150 |
|
56 |
+
| 0.2296 | 3.75 | 120 | 0.4897 | 66.7146 |
|
57 |
+
| 0.1564 | 5.0 | 160 | 0.5131 | 65.3429 |
|
58 |
+
| 0.0905 | 6.25 | 200 | 0.5504 | 63.9035 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151061672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daeea7778cdeda935a2e90f442518eb60512721cd10bce0921a80c47aa8f2543
|
3 |
size 151061672
|
whisper-tiny-hi-checkpoint-1/config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
"decoder_layers": 4,
|
21 |
"decoder_start_token_id": 50258,
|
22 |
-
"dropout": 0.
|
23 |
"encoder_attention_heads": 6,
|
24 |
"encoder_ffn_dim": 1536,
|
25 |
"encoder_layerdrop": 0.0,
|
|
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
"decoder_layers": 4,
|
21 |
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.1,
|
23 |
"encoder_attention_heads": 6,
|
24 |
"encoder_ffn_dim": 1536,
|
25 |
"encoder_layerdrop": 0.0,
|
whisper-tiny-hi-checkpoint-1/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151061672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daeea7778cdeda935a2e90f442518eb60512721cd10bce0921a80c47aa8f2543
|
3 |
size 151061672
|
whisper-tiny-hi-checkpoint-1/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37c1d71d4573028fde34dd156869c75306de202ae193d1b60195dcab72289f8d
|
3 |
size 5240
|