joydeep bhattacharjee
tamil model with wav2vec2, version1 1f70867
1
---
2
language: ta
3
datasets:
4
- common_voice 
5
metrics:
6
- wer
7
tags:
8
- audio
9
- automatic-speech-recognition
10
- speech
11
- xlsr-fine-tuning-week
12
license: apache-2.0
13
model-index:
14
- name: Joydeep Bhattacharjee XLSR Wav2Vec2 Large 53 Tamil
15
  results:
16
  - task: 
17
      name: Speech Recognition
18
      type: automatic-speech-recognition
19
    dataset:
20
      name: Common Voice ta
21
      type: common_voice
22
      args: ta
23
    metrics:
24
       - name: Test WER
25
         type: wer
26
         value: 71.29
27
---
28
# Wav2Vec2-Large-XLSR-53-Tamil
29
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Tamil using the [Common Voice](https://huggingface.co/datasets/common_voice).
30
When using this model, make sure that your speech input is sampled at 16kHz.
31
## Usage
32
The model can be used directly (without a language model) as follows:
33
```python
34
import torch
35
import torchaudio
36
from datasets import load_dataset
37
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
38
test_dataset = load_dataset("common_voice", "ta", split="test[:2%]")
39
processor = Wav2Vec2Processor.from_pretrained("infinitejoy/Wav2Vec2-Large-XLSR-53-Tamil")
40
model = Wav2Vec2ForCTC.from_pretrained("infinitejoy/Wav2Vec2-Large-XLSR-53-Tamil")
41
resampler = torchaudio.transforms.Resample(48_000, 16_000)
42
# Preprocessing the datasets.
43
# We need to read the aduio files as arrays
44
def speech_file_to_array_fn(batch):
45
    speech_array, sampling_rate = torchaudio.load(batch["path"])
46
    batch["speech"] = resampler(speech_array).squeeze().numpy()
47
    return batch
48
test_dataset = test_dataset.map(speech_file_to_array_fn)
49
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
50
with torch.no_grad():
51
    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
52
predicted_ids = torch.argmax(logits, dim=-1)
53
print("Prediction:", processor.batch_decode(predicted_ids))
54
print("Reference:", test_dataset["sentence"][:2])
55
```
56
## Evaluation
57
The model can be evaluated as follows on the Tamil test data of Common Voice.
58
```python
59
import torch
60
import torchaudio
61
from datasets import load_dataset, load_metric
62
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
63
import re
64
test_dataset = load_dataset("common_voice", "ta", split="test")
65
wer = load_metric("wer")
66
processor = Wav2Vec2Processor.from_pretrained("infinitejoy/Wav2Vec2-Large-XLSR-53-Tamil")
67
model = Wav2Vec2ForCTC.from_pretrained("infinitejoy/Wav2Vec2-Large-XLSR-53-Tamil")
68
model.to("cuda")
69
chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\’\–\(\)]'
70
resampler = torchaudio.transforms.Resample(48_000, 16_000)
71
# Preprocessing the datasets.
72
# We need to read the aduio files as arrays
73
def speech_file_to_array_fn(batch):
74
    batch["sentence"] = re.sub('’ ',' ',batch["sentence"])
75
    batch["sentence"] = re.sub(' ‘',' ',batch["sentence"])
76
    batch["sentence"] = re.sub('’|‘','\'',batch["sentence"])
77
    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
78
    speech_array, sampling_rate = torchaudio.load(batch["path"])
79
    batch["speech"] = resampler(speech_array).squeeze().numpy()
80
    return batch
81
test_dataset = test_dataset.map(speech_file_to_array_fn)
82
# Preprocessing the datasets.
83
# We need to read the aduio files as arrays
84
def evaluate(batch):
85
    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
86
    with torch.no_grad():
87
        logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
88
    pred_ids = torch.argmax(logits, dim=-1)
89
    batch["pred_strings"] = processor.batch_decode(pred_ids)
90
    return batch
91
result = test_dataset.map(evaluate, batched=True, batch_size=8)
92
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
93
```
94
**Test Result**: 71.29 % 
95
## Training
96
The Common Voice `train` and `validation` datasets were used for training.
97