marinone94
commited on
Merge branch 'main' of https://huggingface.co/marinone94/whisper-tiny-sv
Browse files
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- 'no'
|
4 |
+
- sv
|
5 |
+
- da
|
6 |
+
license: apache-2.0
|
7 |
+
tags:
|
8 |
+
- whisper-event
|
9 |
+
- generated_from_trainer
|
10 |
+
datasets:
|
11 |
+
- mozilla-foundation/common_voice_11_0
|
12 |
+
- mozilla-foundation/common_voice_11_0
|
13 |
+
- mozilla-foundation/common_voice_11_0
|
14 |
+
- babelbox/babelbox_voice
|
15 |
+
- NbAiLab/NST
|
16 |
+
- NbAiLab/NPSC
|
17 |
+
- google/fleurs
|
18 |
+
- google/fleurs
|
19 |
+
- google/fleurs
|
20 |
+
metrics:
|
21 |
+
- wer
|
22 |
+
model-index:
|
23 |
+
- name: Whisper Tiny Nordic
|
24 |
+
results:
|
25 |
+
- task:
|
26 |
+
name: Automatic Speech Recognition
|
27 |
+
type: automatic-speech-recognition
|
28 |
+
metrics:
|
29 |
+
- name: Wer
|
30 |
+
type: wer
|
31 |
+
value: 87.65957446808511
|
32 |
+
---
|
33 |
+
|
34 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
35 |
+
should probably proofread and complete it, then remove this comment. -->
|
36 |
+
|
37 |
+
# Whisper Tiny Nordic
|
38 |
+
|
39 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the mozilla-foundation/common_voice_11_0 sv-SE
|
40 |
+
mozilla-foundation/common_voice_11_0 da
|
41 |
+
mozilla-foundation/common_voice_11_0 nn-NO
|
42 |
+
babelbox/babelbox_voice nst
|
43 |
+
NbAiLab/NST no-distant
|
44 |
+
NbAiLab/NPSC 16K_mp3_nynorsk
|
45 |
+
google/fleurs sv_se
|
46 |
+
google/fleurs da_dk
|
47 |
+
google/fleurs nb_no dataset.
|
48 |
+
It achieves the following results on the evaluation set:
|
49 |
+
- Loss: 5.1226
|
50 |
+
- Wer: 87.6596
|
51 |
+
|
52 |
+
## Model description
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Intended uses & limitations
|
57 |
+
|
58 |
+
More information needed
|
59 |
+
|
60 |
+
## Training and evaluation data
|
61 |
+
|
62 |
+
More information needed
|
63 |
+
|
64 |
+
## Training procedure
|
65 |
+
|
66 |
+
### Training hyperparameters
|
67 |
+
|
68 |
+
The following hyperparameters were used during training:
|
69 |
+
- learning_rate: 1e-05
|
70 |
+
- train_batch_size: 1
|
71 |
+
- eval_batch_size: 1
|
72 |
+
- seed: 42
|
73 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
+
- lr_scheduler_type: linear
|
75 |
+
- lr_scheduler_warmup_steps: 500
|
76 |
+
- training_steps: 1
|
77 |
+
- mixed_precision_training: Native AMP
|
78 |
+
|
79 |
+
### Training results
|
80 |
+
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.26.0.dev0
|
86 |
+
- Pytorch 1.13.1+cu117
|
87 |
+
- Datasets 2.7.1.dev0
|
88 |
+
- Tokenizers 0.13.2
|