warmestman
commited on
Commit
•
fad5494
1
Parent(s):
8c9b66a
End of training
Browse files- README.md +19 -13
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -26,7 +26,7 @@ model-index:
|
|
26 |
metrics:
|
27 |
- name: Wer
|
28 |
type: wer
|
29 |
-
value:
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -36,8 +36,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
36 |
|
37 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 16.1 & FLEURS dataset.
|
38 |
It achieves the following results on the evaluation set:
|
39 |
-
- Loss: 0.
|
40 |
-
- Wer:
|
41 |
|
42 |
## Model description
|
43 |
|
@@ -56,29 +56,35 @@ More information needed
|
|
56 |
### Training hyperparameters
|
57 |
|
58 |
The following hyperparameters were used during training:
|
59 |
-
- learning_rate:
|
60 |
- train_batch_size: 16
|
61 |
- eval_batch_size: 8
|
62 |
- seed: 42
|
63 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
- lr_scheduler_type: linear
|
65 |
- lr_scheduler_warmup_steps: 500
|
66 |
-
- training_steps:
|
67 |
- mixed_precision_training: Native AMP
|
68 |
|
69 |
### Training results
|
70 |
|
71 |
-
| Training Loss | Epoch | Step
|
72 |
-
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
|
79 |
### Framework versions
|
80 |
|
81 |
-
- Transformers 4.
|
82 |
-
- Pytorch
|
83 |
- Datasets 2.17.0
|
84 |
- Tokenizers 0.15.2
|
|
|
26 |
metrics:
|
27 |
- name: Wer
|
28 |
type: wer
|
29 |
+
value: 31.994939772289754
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
36 |
|
37 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 16.1 & FLEURS dataset.
|
38 |
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.5662
|
40 |
+
- Wer: 31.9949
|
41 |
|
42 |
## Model description
|
43 |
|
|
|
56 |
### Training hyperparameters
|
57 |
|
58 |
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 0.0001
|
60 |
- train_batch_size: 16
|
61 |
- eval_batch_size: 8
|
62 |
- seed: 42
|
63 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
- lr_scheduler_type: linear
|
65 |
- lr_scheduler_warmup_steps: 500
|
66 |
+
- training_steps: 10000
|
67 |
- mixed_precision_training: Native AMP
|
68 |
|
69 |
### Training results
|
70 |
|
71 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
72 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
|
73 |
+
| 0.0691 | 5.99 | 1000 | 0.4597 | 41.5049 |
|
74 |
+
| 0.0183 | 11.98 | 2000 | 0.4996 | 38.2982 |
|
75 |
+
| 0.012 | 17.96 | 3000 | 0.5328 | 38.5402 |
|
76 |
+
| 0.0091 | 23.95 | 4000 | 0.5619 | 38.1277 |
|
77 |
+
| 0.004 | 29.94 | 5000 | 0.5439 | 35.2236 |
|
78 |
+
| 0.0019 | 35.93 | 6000 | 0.5731 | 35.3941 |
|
79 |
+
| 0.001 | 41.92 | 7000 | 0.5309 | 33.3755 |
|
80 |
+
| 0.0002 | 47.9 | 8000 | 0.5391 | 32.3140 |
|
81 |
+
| 0.0 | 53.89 | 9000 | 0.5543 | 32.1984 |
|
82 |
+
| 0.0 | 59.88 | 10000 | 0.5662 | 31.9949 |
|
83 |
|
84 |
|
85 |
### Framework versions
|
86 |
|
87 |
+
- Transformers 4.38.0.dev0
|
88 |
+
- Pytorch 2.2.0+cu121
|
89 |
- Datasets 2.17.0
|
90 |
- Tokenizers 0.15.2
|
generation_config.json
CHANGED
@@ -261,5 +261,5 @@
|
|
261 |
"transcribe": 50360,
|
262 |
"translate": 50359
|
263 |
},
|
264 |
-
"transformers_version": "4.
|
265 |
}
|
|
|
261 |
"transcribe": 50360,
|
262 |
"translate": 50359
|
263 |
},
|
264 |
+
"transformers_version": "4.38.0.dev0"
|
265 |
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4993448880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e971a5194ba027488dfa2604d64eaaa0f1c8bd7fd5fd461d4190e15878642d1f
|
3 |
size 4993448880
|
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:aa895cc7bf9bae9de82a668e609b652e1e49d98ddece27b00eb3fac6bba1a884
|
3 |
size 1180663192
|