1
---
2
language: eu
3
datasets:
4
- common_voice
5
tags:
6
- audio
7
- automatic-speech-recognition
8
- speech
9
- xlsr-fine-tuning-week
10
license: apache-2.0
11
model-index:
12
- name: XLSR Wav2Vec2 Euskera Manuel Romero
13
  results:
14
  - task: 
15
      name: Speech Recognition
16
      type: automatic-speech-recognition
17
    dataset:
18
      name: Common Voice eu
19
      type: common_voice
20
      args: eu
21
    metrics:
22
       - name: Test WER
23
         type: wer
24
         value: 24.03
25
---
26
27
# Wav2Vec2-Large-XLSR-53-euskera
28
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Euskera using the [Common Voice](https://huggingface.co/datasets/common_voice).
29
When using this model, make sure that your speech input is sampled at 16kHz.
30
31
## Usage
32
33
The model can be used directly (without a language model) as follows:
34
35
```python
36
import torch
37
import torchaudio
38
from datasets import load_dataset
39
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
40
41
test_dataset = load_dataset("common_voice", "eu", split="test[:2%]").
42
43
processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-euskera")
44
model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-euskera")
45
46
resampler = torchaudio.transforms.Resample(48_000, 16_000)
47
48
# Preprocessing the datasets.
49
# We need to read the aduio files as arrays
50
def speech_file_to_array_fn(batch):
51
  speech_array, sampling_rate = torchaudio.load(batch["path"])
52
  batch["speech"] = resampler(speech_array).squeeze().numpy()
53
  return batch
54
55
test_dataset = test_dataset.map(speech_file_to_array_fn)
56
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
57
58
with torch.no_grad():
59
  logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
60
61
predicted_ids = torch.argmax(logits, dim=-1)
62
63
print("Prediction:", processor.batch_decode(predicted_ids))
64
print("Reference:", test_dataset["sentence"][:2])
65
```
66
67
68
## Evaluation
69
70
The model can be evaluated as follows on the Euskera test data of Common Voice.
71
72
73
```python
74
import torch
75
import torchaudio
76
from datasets import load_dataset, load_metric
77
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
78
import re
79
80
test_dataset = load_dataset("common_voice", "eu", split="test")
81
wer = load_metric("wer")
82
83
processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-euskera")
84
model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-euskera")
85
model.to("cuda")
86
87
chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�]'
88
resampler = torchaudio.transforms.Resample(48_000, 16_000)
89
90
# Preprocessing the datasets.
91
# We need to read the aduio files as arrays
92
def speech_file_to_array_fn(batch):
93
  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
94
  speech_array, sampling_rate = torchaudio.load(batch["path"])
95
  batch["speech"] = resampler(speech_array).squeeze().numpy()
96
  return batch
97
98
test_dataset = test_dataset.map(speech_file_to_array_fn)
99
100
# Preprocessing the datasets.
101
# We need to read the aduio files as arrays
102
def evaluate(batch):
103
  inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
104
105
  with torch.no_grad():
106
    logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
107
108
  pred_ids = torch.argmax(logits, dim=-1)
109
  batch["pred_strings"] = processor.batch_decode(pred_ids)
110
  return batch
111
112
result = test_dataset.map(evaluate, batched=True, batch_size=8)
113
114
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
115
```
116
117
**Test Result**: 24.03 %
118
119
120
## Training
121
122
The Common Voice `train`, `validation` datasets were used for training.
123
124
The script used for training can be found ???
125