Hugging Face's logo

alokmatta
/
wav2vec2-large-xlsr-53-sw

Automatic Speech Recognition
Transformers
PyTorch
JAX
Swahili
wav2vec2
audio
speech
xlsr-fine-tuning-week
Inference Endpoints
Model card Files Community
1
alokmatta commited on
Commit
52ee1eb
·
1 Parent(s): 921e190

links fix

Browse files
Files changed (1) hide show
  1. README.md +8 -3
README.md CHANGED
@@ -1,7 +1,9 @@
1
  ---
2
  language: sw
3
  datasets:
4
- - ALFFA (African Languages in the Field: speech Fundamentals and Automation) - [here](http://www.openslr.org/25/), Gamayun [here]https://gamayun.translatorswb.org/download/gamayun-5k-english-swahili/ & IWSLT [here]https://iwslt.org/2021/low-resource
 
 
5
 
6
  metrics:
7
  - wer
@@ -28,7 +30,10 @@ model-index:
28
 
29
  # Wav2Vec2-Large-XLSR-53-Swahili
30
 
31
- Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Swahili using the [ALFFA](http://www.openslr.org/25/), Gamayun [here]https://gamayun.translatorswb.org/download/gamayun-5k-english-swahili/ & IWSLT [here]https://iwslt.org/2021/low-resource datasets.
 
 
 
32
 
33
  When using this model, make sure that your speech input is sampled at 16kHz.
34
 
@@ -77,4 +82,4 @@ predict(load_file_to_data('./demo.wav'))
77
  ## Training
78
 
79
 
80
- The script used for training can be found [here]https://colab.research.google.com/drive/1_RL6TQv_Yiu_xbWXu4ycbzdCdXCqEQYU?usp=sharing
 
1
  ---
2
  language: sw
3
  datasets:
4
+ - [ALFFA](http://www.openslr.org/25)
5
+ - [Gamayun](https://gamayun.translatorswb.org/download/gamayun-5k-english-swahili/)
6
+ - [IWSLT](https://iwslt.org/2021/low-resource)
7
 
8
  metrics:
9
  - wer
 
30
 
31
  # Wav2Vec2-Large-XLSR-53-Swahili
32
 
33
+ Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Swahili using the following datasets:
34
+ - [ALFFA](http://www.openslr.org/25/),
35
+ - [Gamayun](https://gamayun.translatorswb.org/download/gamayun-5k-english-swahili/)
36
+ - [IWSLT](https://iwslt.org/2021/low-resource)
37
 
38
  When using this model, make sure that your speech input is sampled at 16kHz.
39
 
 
82
  ## Training
83
 
84
 
85
+ The script used for training can be found [here](https://colab.research.google.com/drive/1_RL6TQv_Yiu_xbWXu4ycbzdCdXCqEQYU?usp=sharing)