Hugging Face's logo

tanmoyio
/
wav2vec2-large-xlsr-bengali

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results
Inference Endpoints
Model card Files Community
1
patrickvonplaten commited on
Commit
000ae0c
•
1 Parent(s): 1b1129b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  dataset:
20
  name: OpenSLR
21
  type: OpenSLR
22
- args: or
23
  metrics:
24
  - name: Test WER
25
  type: wer
@@ -32,7 +32,7 @@ When using this model, make sure that your speech input is sampled at 16kHz.
32
  Dataset must be downloaded from [this website](https://www.openslr.org/53/) and preprocessed accordingly. For example 1250 test samples has been chosen.
33
  ```python
34
  import pandas as pd
35
- test_dataset = pd.read_csv('utt_spk_text.tsv', sep='\t', header=None)[60000:61250]
36
  test_dataset.columns = ["audio_path", "__", "label"]
37
  test_dataset = test_data.drop("__", axis=1)
38
  def add_file_path(text):
19
  dataset:
20
  name: OpenSLR
21
  type: OpenSLR
22
+ args: ben
23
  metrics:
24
  - name: Test WER
25
  type: wer
32
  Dataset must be downloaded from [this website](https://www.openslr.org/53/) and preprocessed accordingly. For example 1250 test samples has been chosen.
33
  ```python
34
  import pandas as pd
35
+ test_dataset = pd.read_csv('utt_spk_text.tsv', sep='\\t', header=None)[60000:61250]
36
  test_dataset.columns = ["audio_path", "__", "label"]
37
  test_dataset = test_data.drop("__", axis=1)
38
  def add_file_path(text):