tanmaylaud commited on
Commit
863a64d
1 Parent(s): cb7ac4f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -3
README.md CHANGED
@@ -1,5 +1,35 @@
1
- # Wav2Vec2-Large-XLSR-53-Marathi
2
- ### Fine-tuned facebook/wav2vec2-large-xlsr-53 on Marathi using the OpenSLR SLR64 dataset and InterSpeech 2021 Marathi datasets. Note that this data OpenSLR contains only female voices. Please keep this in mind before using the model for your task. When using this model, make sure that your speech input is sampled at 16kHz.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
 
4
  ## Usage
5
  The model can be used directly (without a language model) as follows, assuming you have a dataset with Marathi text and audio_path fields:
@@ -51,7 +81,7 @@ processor = Wav2Vec2Processor.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr
51
  model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr-3")
52
  model.to("cuda")
53
 
54
- chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\–\…]'
55
 
56
 
57
  # Preprocessing the datasets.
1
+ ---
2
+ language: mr
3
+ datasets:
4
+ - openslr
5
+ - interspeech_2021_asr
6
+ metrics:
7
+ - wer
8
+ tags:
9
+ - audio
10
+ - automatic-speech-recognition
11
+ - speech
12
+ - xlsr-fine-tuning-week
13
+ - hindi
14
+ - marathi
15
+ license: apache-2.0
16
+ model-index:
17
+ - name: XLSR Wav2Vec2 Large 53 Hindi-Marathi by Tanmay Laud
18
+ results:
19
+ - task:
20
+ name: Speech Recognition
21
+ type: automatic-speech-recognition
22
+ dataset:
23
+ name: OpenSLR hi, OpenSLR mr
24
+ type: openslr, interspeech_2021_asr
25
+ metrics:
26
+ - name: Test WER
27
+ type: wer
28
+ value: 60.80
29
+ ---
30
+
31
+ # Wav2Vec2-Large-XLSR-53-Hindi-Marathi
32
+ ### Fine-tuned facebook/wav2vec2-large-xlsr-53 on Hindi and Marathi using the OpenSLR SLR64 datasets. Note that this data OpenSLR contains only female voices. Please keep this in mind before using the model for your task. When using this model, make sure that your speech input is sampled at 16kHz.
33
 
34
  ## Usage
35
  The model can be used directly (without a language model) as follows, assuming you have a dataset with Marathi text and audio_path fields:
81
  model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr-3")
82
  model.to("cuda")
83
 
84
+ chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\–\\…]'
85
 
86
 
87
  # Preprocessing the datasets.