Prepared for changing ownership to CLASSLA
Browse files
README.md
CHANGED
@@ -14,7 +14,7 @@ widget:
|
|
14 |
src: https://huggingface.co/classla/wav2vec2-xls-r-parlaspeech-hr/raw/main/00020570a.flac.wav
|
15 |
---
|
16 |
|
17 |
-
# wav2vec2-
|
18 |
|
19 |
This model for Serbian ASR is based on the [facebook/wav2vec2-xls-r-300m model](https://huggingface.co/facebook/wav2vec2-xls-r-300m) and was fine-tuned with 58 hours of audio and transcripts from [Južne vesti](https://www.juznevesti.com/), programme '15 minuta'.
|
20 |
|
@@ -45,8 +45,8 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
|
|
45 |
|
46 |
# load model and tokenizer
|
47 |
processor = Wav2Vec2Processor.from_pretrained(
|
48 |
-
"
|
49 |
-
model = Wav2Vec2ForCTC.from_pretrained("
|
50 |
|
51 |
|
52 |
# download the example wav files:
|
|
|
14 |
src: https://huggingface.co/classla/wav2vec2-xls-r-parlaspeech-hr/raw/main/00020570a.flac.wav
|
15 |
---
|
16 |
|
17 |
+
# wav2vec2-xls-r-juznevesti
|
18 |
|
19 |
This model for Serbian ASR is based on the [facebook/wav2vec2-xls-r-300m model](https://huggingface.co/facebook/wav2vec2-xls-r-300m) and was fine-tuned with 58 hours of audio and transcripts from [Južne vesti](https://www.juznevesti.com/), programme '15 minuta'.
|
20 |
|
|
|
45 |
|
46 |
# load model and tokenizer
|
47 |
processor = Wav2Vec2Processor.from_pretrained(
|
48 |
+
"classla/wav2vec2-xls-r-juznevesti-sr")
|
49 |
+
model = Wav2Vec2ForCTC.from_pretrained("classla/wav2vec2-xls-r-juznevesti-sr")
|
50 |
|
51 |
|
52 |
# download the example wav files:
|