1
---
2
language: et
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: common-voice-vox-populi-swedish by Birger Moell
13
  results:
14
  - task: 
15
      name: Speech Recognition
16
      type: automatic-speech-recognition
17
    dataset:
18
      name: Common Voice Vox Populi Swedish
19
      type: common_voice
20
      args: et 
21
    metrics:
22
       - name: Test WER
23
         type: wer
24
         value: 36.951816
25
---
26
27
28
29
30
# common-voice-vox-populi-swedish
31
32
Fine-tuned [facebook/wav2vec2-large-sv-voxpopuli](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Swedish using the [Common Voice](https://huggingface.co/datasets/common_voice)
33
When using this model, make sure that your speech input is sampled at 16kHz.
34
35
## Usage
36
37
The model can be used directly (without a language model) as follows:
38
39
```python
40
import torch
41
import torchaudio
42
from datasets import load_dataset
43
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
44
45
test_dataset = load_dataset("common_voice", "sv-SE", split="test[:2%]").
46
47
processor = Wav2Vec2Processor.from_pretrained("birgermoell/birgermoell/common-voice-vox-populi-swedish")
48
model = Wav2Vec2ForCTC.from_pretrained("birgermoell/common-voice-vox-populi-swedish")
49
50
resampler = torchaudio.transforms.Resample(48_000, 16_000)
51
52
# Preprocessing the datasets.
53
# We need to read the aduio files as arrays
54
def speech_file_to_array_fn(batch):
55
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
56
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
57
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\treturn batch
58
59
test_dataset = test_dataset.map(speech_file_to_array_fn)
60
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
61
62
with torch.no_grad():
63
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
64
65
predicted_ids = torch.argmax(logits, dim=-1)
66
67
print("Prediction:", processor.batch_decode(predicted_ids))
68
print("Reference:", test_dataset["sentence"][:2])
69
```
70
71
72
## Evaluation
73
74
The model can be evaluated as follows on the Swedish test data of Common Voice.
75
76
77
```python
78
import torch
79
import torchaudio
80
from datasets import load_dataset, load_metric
81
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
82
import re
83
84
test_dataset = load_dataset("common_voice", "sv-SE", split="test")
85
wer = load_metric("wer")
86
87
processor = Wav2Vec2Processor.from_pretrained("birgermoell/common-voice-vox-populi-swedish")
88
model = Wav2Vec2ForCTC.from_pretrained("birgermoell/common-voice-vox-populi-swedish")
89
model.to("cuda")
90
91
chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“]'
92
resampler = torchaudio.transforms.Resample(48_000, 16_000)
93
94
# Preprocessing the datasets.
95
# We need to read the aduio files as arrays
96
def speech_file_to_array_fn(batch):
97
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
98
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
99
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
100
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\treturn batch
101
102
test_dataset = test_dataset.map(speech_file_to_array_fn)
103
104
# Preprocessing the datasets.
105
# We need to read the aduio files as arrays
106
def evaluate(batch):
107
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
108
109
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\twith torch.no_grad():
110
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\t\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
111
    pred_ids = torch.argmax(logits, dim=-1)
112
    
113
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
114
\\\\\\\\\\\\\\\\\\\\
115
116
```
117
**Test Result**:
118
WER: 22.684600 
119