Commit
•
4e27da9
1
Parent(s):
a206e52
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# finetuned-wav2vec2-960h
|
| 2 |
+
|
| 3 |
+
This model was trained as a part of my **GSoC'21 (Google Summer of Code)** project. It is fine-tuned on 960h of **LibriSpeech dataset** (`train-clean-100`, `train-clean-360`, `train-other-500`) and evaluated on `test-clean` data.
|
| 4 |
+
|
| 5 |
+
| WER (word error rate) | 5.67 |
|
| 6 |
+
|-----------------------|------|
|
| 7 |
+
|
| 8 |
+
You can find code for training here: https://github.com/vasudevgupta7/gsoc-wav2vec2.
|