End of training
Browse files- README.md +17 -13
- generation_config.json +1 -1
README.md
CHANGED
@@ -1,23 +1,31 @@
|
|
1 |
---
|
2 |
language:
|
3 |
-
-
|
4 |
license: apache-2.0
|
5 |
base_model: openai/whisper-small
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
model-index:
|
11 |
-
- name: Whisper Small
|
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
|
19 |
|
20 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,20 +44,16 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate:
|
40 |
- train_batch_size: 32
|
41 |
-
- eval_batch_size:
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- lr_scheduler_warmup_steps:
|
46 |
-
- training_steps:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
-
### Training results
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
### Framework versions
|
54 |
|
55 |
- Transformers 4.39.3
|
|
|
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 |
+
- mShiry/ATC_combined
|
10 |
model-index:
|
11 |
+
- name: Whisper Small ATC - ATCText
|
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 ATC - ATCText
|
19 |
|
20 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the ATC dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- eval_loss: 1.9991
|
23 |
+
- eval_wer: 76.1224
|
24 |
+
- eval_runtime: 2033.5597
|
25 |
+
- eval_samples_per_second: 2.323
|
26 |
+
- eval_steps_per_second: 0.066
|
27 |
+
- epoch: 0.0
|
28 |
+
- step: 1
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
44 |
### Training hyperparameters
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 0.1
|
48 |
- train_batch_size: 32
|
49 |
+
- eval_batch_size: 35
|
50 |
- seed: 42
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
+
- lr_scheduler_warmup_steps: 500
|
54 |
+
- training_steps: 2
|
55 |
- mixed_precision_training: Native AMP
|
56 |
|
|
|
|
|
|
|
|
|
57 |
### Framework versions
|
58 |
|
59 |
- Transformers 4.39.3
|
generation_config.json
CHANGED
@@ -150,7 +150,7 @@
|
|
150 |
"<|yo|>": 50325,
|
151 |
"<|zh|>": 50260
|
152 |
},
|
153 |
-
"language": "
|
154 |
"max_initial_timestamp_index": 50,
|
155 |
"max_length": 448,
|
156 |
"no_timestamps_token_id": 50363,
|
|
|
150 |
"<|yo|>": 50325,
|
151 |
"<|zh|>": 50260
|
152 |
},
|
153 |
+
"language": "english",
|
154 |
"max_initial_timestamp_index": 50,
|
155 |
"max_length": 448,
|
156 |
"no_timestamps_token_id": 50363,
|