Commit
•
b3d8654
1
Parent(s):
84c714a
Update README.md
Browse files
README.md
CHANGED
|
@@ -130,9 +130,6 @@ This model is the result of four different stages of training:
|
|
| 130 |
dataset](https://huggingface.co/datasets/alexandrainst/coral) (revision
|
| 131 |
fb20199b3966d3373e0d3a5ded2c5920c70de99c), consisting of 361 hours of Danish
|
| 132 |
read-aloud speech, diverse across dialects, accents, ages and genders.
|
| 133 |
-
- The Danish training split of the [Common Voice 17
|
| 134 |
-
dataset](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0),
|
| 135 |
-
consisting of 12 hours of Danish read-aloud speech.
|
| 136 |
3. An n-gram language model has been trained separately, and is used to guide the
|
| 137 |
transcription generation of the finetuned speech recognition model. This n-gram
|
| 138 |
language model has been trained on the following datasets:
|
|
|
|
| 130 |
dataset](https://huggingface.co/datasets/alexandrainst/coral) (revision
|
| 131 |
fb20199b3966d3373e0d3a5ded2c5920c70de99c), consisting of 361 hours of Danish
|
| 132 |
read-aloud speech, diverse across dialects, accents, ages and genders.
|
|
|
|
|
|
|
|
|
|
| 133 |
3. An n-gram language model has been trained separately, and is used to guide the
|
| 134 |
transcription generation of the finetuned speech recognition model. This n-gram
|
| 135 |
language model has been trained on the following datasets:
|