cahya commited on
Commit
b69759c
1 Parent(s): e047dc5

updated the link to the model

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -29,9 +29,9 @@ model-index:
29
  # Wav2Vec2-Large-XLSR-Turkish
30
 
31
  This is the model for Wav2Vec2-Large-XLSR-Turkish-Artificial-CV, a fine-tuned
32
- [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53)
33
- model on the Synthetic Turkish Voice dataset and
34
- [Turkish Common Voice dataset](https://huggingface.co/datasets/common_voice).
35
  When using this model, make sure that your speech input is sampled at 16kHz.
36
 
37
  ## Usage
@@ -44,8 +44,8 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
44
 
45
  test_dataset = load_dataset("common_voice", "tr", split="test[:2%]")
46
 
47
- processor = Wav2Vec2Processor.from_pretrained("cahya-wirawan/wav2vec2-large-xlsr-turkish-artificial-cv")
48
- model = Wav2Vec2ForCTC.from_pretrained("cahya-wirawan/wav2vec2-large-xlsr-turkish-artificial-cv")
49
 
50
 
51
  # Preprocessing the datasets.
@@ -83,8 +83,8 @@ import re
83
  test_dataset = load_dataset("common_voice", "tr", split="test")
84
  wer = load_metric("wer")
85
 
86
- processor = Wav2Vec2Processor.from_pretrained("cahya-wirawan/wav2vec2-large-xlsr-turkish-artificial-cv")
87
- model = Wav2Vec2ForCTC.from_pretrained("cahya-wirawan/wav2vec2-large-xlsr-turkish-artificial-cv")
88
  model.to("cuda")
89
 
90
  chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\‘\”\'\`…\’»«]'
 
29
  # Wav2Vec2-Large-XLSR-Turkish
30
 
31
  This is the model for Wav2Vec2-Large-XLSR-Turkish-Artificial-CV, a fine-tuned
32
+ [cahya/wav2vec2-large-xlsr-turkish-artificial](https://huggingface.co/cahya/wav2vec2-large-xlsr-turkish-artificial)
33
+ model on [Turkish Common Voice dataset](https://huggingface.co/datasets/common_voice).
34
+
35
  When using this model, make sure that your speech input is sampled at 16kHz.
36
 
37
  ## Usage
 
44
 
45
  test_dataset = load_dataset("common_voice", "tr", split="test[:2%]")
46
 
47
+ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial-cv")
48
+ model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial-cv")
49
 
50
 
51
  # Preprocessing the datasets.
 
83
  test_dataset = load_dataset("common_voice", "tr", split="test")
84
  wer = load_metric("wer")
85
 
86
+ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial-cv")
87
+ model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial-cv")
88
  model.to("cuda")
89
 
90
  chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\‘\”\'\`…\’»«]'