Delete README.md
Browse files
README.md
DELETED
@@ -1,30 +0,0 @@
|
|
1 |
-
---
|
2 |
-
language: sv
|
3 |
-
license: apache-2.0
|
4 |
-
tags:
|
5 |
-
- seq-2-seq asr
|
6 |
-
- whisper
|
7 |
-
datasets:
|
8 |
-
- mozilla-foundation/common_voice_11_0
|
9 |
-
library_name: torch
|
10 |
-
---
|
11 |
-
|
12 |
-
## Model description
|
13 |
-
|
14 |
-
This model is a fine-tuned version of OpenAI's pre-trained Whisper small. [Source](https://github.com/openai/whisper)
|
15 |
-
|
16 |
-
The model were trained on 680 000 hours of audio with corresponding transcripts from the internet, 65% of which was in english audio and 83 % of which had english transcripts.
|
17 |
-
|
18 |
-
The model was then further trained for 4000 iterations, 500 of which as warm-up, on Swedish data from [Common_voice 11.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0). Achieving a WER of 19.865.
|
19 |
-
|
20 |
-
|
21 |
-
## Training Metrics
|
22 |
-
![Training table](whisper_finetune.png)
|
23 |
-
## Model Plot
|
24 |
-
|
25 |
-
<details>
|
26 |
-
<summary>View Training Plots</summary>
|
27 |
-
|
28 |
-
![Metrics](whisper_metrics.png)
|
29 |
-
|
30 |
-
</details>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|