Commit
•
1ff300c
1
Parent(s):
a81c70c
End of training
Browse files
README.md
CHANGED
@@ -8,24 +8,9 @@ tags:
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- mozilla-foundation/common_voice_11_0
|
11 |
-
metrics:
|
12 |
-
- wer
|
13 |
model-index:
|
14 |
- name: Whisper Small sv-SE augmented data tuned model
|
15 |
-
results:
|
16 |
-
- task:
|
17 |
-
name: Automatic Speech Recognition
|
18 |
-
type: automatic-speech-recognition
|
19 |
-
dataset:
|
20 |
-
name: Common Voice 11.0
|
21 |
-
type: mozilla-foundation/common_voice_11_0
|
22 |
-
config: sv-SE
|
23 |
-
split: test
|
24 |
-
args: 'config: sv-SE, split: test'
|
25 |
-
metrics:
|
26 |
-
- name: Wer
|
27 |
-
type: wer
|
28 |
-
value: 27.396413110698823
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -35,8 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
-
|
39 |
-
-
|
|
|
|
|
|
|
|
|
|
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -64,19 +54,9 @@ The following hyperparameters were used during training:
|
|
64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
- lr_scheduler_type: linear
|
66 |
- lr_scheduler_warmup_steps: 10
|
67 |
-
- training_steps:
|
68 |
- mixed_precision_training: Native AMP
|
69 |
|
70 |
-
### Training results
|
71 |
-
|
72 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
73 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
74 |
-
| 0.7456 | 0.26 | 200 | 0.6935 | 45.3040 |
|
75 |
-
| 0.6126 | 0.52 | 400 | 0.5469 | 37.3235 |
|
76 |
-
| 0.5114 | 0.78 | 600 | 0.4381 | 31.7362 |
|
77 |
-
| 0.1135 | 1.04 | 800 | 0.3705 | 27.3964 |
|
78 |
-
|
79 |
-
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.36.0.dev0
|
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- mozilla-foundation/common_voice_11_0
|
|
|
|
|
11 |
model-index:
|
12 |
- name: Whisper Small sv-SE augmented data tuned model
|
13 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- eval_loss: 0.4671
|
24 |
+
- eval_wer: 31.0882
|
25 |
+
- eval_runtime: 2727.495
|
26 |
+
- eval_samples_per_second: 1.858
|
27 |
+
- eval_steps_per_second: 0.232
|
28 |
+
- epoch: 1.3
|
29 |
+
- step: 1000
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
- lr_scheduler_type: linear
|
56 |
- lr_scheduler_warmup_steps: 10
|
57 |
+
- training_steps: 1600
|
58 |
- mixed_precision_training: Native AMP
|
59 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
### Framework versions
|
61 |
|
62 |
- Transformers 4.36.0.dev0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ca9e8df7087d19056469a30ff8431a7e731ba60803d52cd88ecae27ec64f387
|
3 |
size 966995080
|
runs/Dec06_15-54-30_00ede819ba4d/events.out.tfevents.1701878110.00ede819ba4d.6463.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7639d5e9a38b8fe16d1c6c27efbe8b01e9b493fa1045b37ecef3f848b39a81dc
|
3 |
+
size 6501
|
runs/Dec07_13-49-54_48275e1e45e5/events.out.tfevents.1701957103.48275e1e45e5.155.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f25be8efe8033fc9cc0fe81b3494145becc037e3d6a9f80075aa59f376c7b04
|
3 |
+
size 6819
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7bf5167e7c26d1fc100ec83212e6328cfc4e22eafad00d6f62b1119bd3414fd
|
3 |
size 4856
|