Update README.md
Browse files
README.md
CHANGED
|
@@ -31,8 +31,7 @@ widget:
|
|
| 31 |
# NB-Whisper Large - converted for Faster-Whisper using cTranslate2
|
| 32 |
|
| 33 |
|
| 34 |
-
### This model is converted for using together with faster-whisper using cTranslate2.
|
| 35 |
-
### It is a fork of original, and original description is below with original URL's
|
| 36 |
|
| 37 |
|
| 38 |
Introducing the **_Norwegian NB-Whisper Small model_**, proudly developed by the National Library of Norway. NB-Whisper is a cutting-edge series of models designed for automatic speech recognition (ASR) and speech translation. These models are based on the work of [OpenAI's Whisper](https://arxiv.org/abs/2212.04356). Each model in the series has been trained for 250,000 steps, utilizing a diverse dataset of 8 million samples. These samples consist of aligned audio clips, each 30 seconds long, culminating in a staggering 66,000 hours of speech. For an in-depth understanding of our training methodology and dataset composition, keep an eye out for our upcoming article.
|
|
|
|
| 31 |
# NB-Whisper Large - converted for Faster-Whisper using cTranslate2
|
| 32 |
|
| 33 |
|
| 34 |
+
### This model is converted for using together with faster-whisper using cTranslate2. Original description is below with original URL's
|
|
|
|
| 35 |
|
| 36 |
|
| 37 |
Introducing the **_Norwegian NB-Whisper Small model_**, proudly developed by the National Library of Norway. NB-Whisper is a cutting-edge series of models designed for automatic speech recognition (ASR) and speech translation. These models are based on the work of [OpenAI's Whisper](https://arxiv.org/abs/2212.04356). Each model in the series has been trained for 250,000 steps, utilizing a diverse dataset of 8 million samples. These samples consist of aligned audio clips, each 30 seconds long, culminating in a staggering 66,000 hours of speech. For an in-depth understanding of our training methodology and dataset composition, keep an eye out for our upcoming article.
|