Commit
•
311a1cb
1
Parent(s):
1a94387
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Whisper finetuned on Swedish Speech
|
| 2 |
|
| 3 |
Whisper is a state-of-the-art automatic speech recognition(ASR) model created by OpenAI. It is able to translate and transcribe multiple different languages. In this project the "small" Whisper model with 244M parameters was used. The dataset that wasa used for fine-tuning the Whisper model was the Swedish subset of the Mozilla foundation common voice 11 dataset.
|
|
@@ -19,5 +29,4 @@ Each audio in the dataset will be truncated or padded to 30 second snippets and
|
|
| 19 |
| `per_device_eval_batch_size` | 8 |
|
| 20 |
| `generation_max_length` | 225 |
|
| 21 |
| `save_steps` | 250 |
|
| 22 |
-
| `eval_steps` | 250 |
|
| 23 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- mozilla-foundation/common_voice_11_0
|
| 5 |
+
language:
|
| 6 |
+
- sv
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
library_name: transformers
|
| 10 |
+
---
|
| 11 |
# Whisper finetuned on Swedish Speech
|
| 12 |
|
| 13 |
Whisper is a state-of-the-art automatic speech recognition(ASR) model created by OpenAI. It is able to translate and transcribe multiple different languages. In this project the "small" Whisper model with 244M parameters was used. The dataset that wasa used for fine-tuning the Whisper model was the Swedish subset of the Mozilla foundation common voice 11 dataset.
|
|
|
|
| 29 |
| `per_device_eval_batch_size` | 8 |
|
| 30 |
| `generation_max_length` | 225 |
|
| 31 |
| `save_steps` | 250 |
|
| 32 |
+
| `eval_steps` | 250 |
|
|
|