Titouan
commited on
Commit
•
a5b68d9
1
Parent(s):
545d07f
first model
Browse files- README.md +39 -0
- checkpoint_best.pt +3 -0
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: "fr"
|
| 3 |
+
thumbnail:
|
| 4 |
+
tags:
|
| 5 |
+
- automatic-speech-recognition
|
| 6 |
+
- wav2vec2
|
| 7 |
+
license: "apache-2.0"
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# LeBenchmark: wav2vec2 large model training on 3K hours of French speech
|
| 11 |
+
|
| 12 |
+
Some text
|
| 13 |
+
|
| 14 |
+
## description
|
| 15 |
+
|
| 16 |
+
Some text
|
| 17 |
+
|
| 18 |
+
## Intended uses & limitations
|
| 19 |
+
|
| 20 |
+
Some text
|
| 21 |
+
|
| 22 |
+
## Fine-tune with Fairseq (ASR with CTC)
|
| 23 |
+
|
| 24 |
+
Instructions
|
| 25 |
+
|
| 26 |
+
```
|
| 27 |
+
pip install fairseq
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
### Integrate to SpeechBrain (ASR, SLU, Speaker ...)
|
| 31 |
+
|
| 32 |
+
```python
|
| 33 |
+
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
#### Referencing LeBenchmark
|
| 37 |
+
|
| 38 |
+
```
|
| 39 |
+
```
|
checkpoint_best.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b9e84e0e33ae7d29da8203ff6be3c52ab9e7f739ef6988fd545a67c80488d99
|
| 3 |
+
size 3808804403
|