Downloads · 30 days
1.1K
5% of all-time downloads
whisper-large-finnish-v3
Finnish-NLP/whisper-large-finnish-v3
whisper-large-finnish-v3 is a automatic speech recognition model from Finnish-NLP. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
<h3This is our improved Whisper v3 model that is now finetuned from OpenAI Whisper Large V3 </h3 <pWe improve from our previously finetuned Whisper V2 model in the following manner<ahttps://huggingface.co/Finnish-NLP/…
All-time downloads
20.7K
Public
Parameters
1.6B
3.3 GB on disk
Likes
19
Public
Repo makeup
Click a slice to open those files.
.safetensors3.2 GB · 97%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 25, 2023
- Updated
- Aug 1, 2024
- SHA
- b23deb0b
Model card
From the Hugging Face model README
<h3>This is our improved Whisper v3 model that is now finetuned from OpenAI Whisper Large V3 </h3>
<p>We improve from our previously finetuned Whisper V2 model in the following manner<a>https://huggingface.co/Finnish-NLP/whisper-large-v2-finnish</a> </p>
<p>CV11 (Common Voice 11 test set) WER (Word error rate) 10.42 --> 8.23</p>
<p>Fleurs (A speech recognition test set by Google) WER (Word error rate) 10.20 --> 8.21</p>
<p>Model was trained on Nvidia RTX4080 for 32k steps with batch size 8, gradient accumulation 2</p>
<br>
<h3> Original OpenAI Whisper Large V3</h3>
- CV11
- WER: 14.81
- WER NORMALIZED: 10.82
- CER: 2.7
- CER NORMALIZED: 2.07
- Fleurs
- WER: 12.04
- WER NORMALIZED: 9.63
- CER: 2.48
- CER NORMALIZED: 3.64
-
@14000 finetuning steps
-
CV11
- WER: 11.36
- WER NORMALIZED: 8.31
- CER: 1.93
- CER NORMALIZED: 1.48
-
Fleurs
- WER: 10.2
- WER NORMALIZED: 8.56
- CER: 2.26
- CER NORMALIZED: 3.54
-
-
@32000 finetuning steps
-
CV11
- WER: 11.47
- WER NORMALIZED: 8.23
- CER: 1.91
- CER NORMALIZED: 1.43
-
Fleurs
- WER: 10.1
- WER NORMALIZED: 8.21
- CER: 2.2
- CER NORMALIZED: 3.23
-
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- fi
- Created
- Nov 25, 2023
- Updated
- Aug 1, 2024