theainerd commited on
Commit
cfb0bbc
1 Parent(s): 1a7b6bf

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +122 -0
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: or
3
+ datasets:
4
+ - OpenSLR
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: XLSR Wav2Vec2 Odia
15
+ results:
16
+ - task:
17
+ name: Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: OpenSLR
21
+ type: OpenSLR
22
+ args: or
23
+ metrics:
24
+ - name: Test WER
25
+ type: wer
26
+ value: 68.75
27
+ ---
28
+
29
+ # Wav2Vec2-Large-XLSR-53-Odia
30
+
31
+ Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) odia using the [Multilingual and code-switching ASR challenges for low resource Indian languages](https://navana-tech.github.io/IS21SS-indicASRchallenge/data.html).
32
+ When using this model, make sure that your speech input is sampled at 16kHz.
33
+
34
+ ## Usage
35
+
36
+ The model can be used directly (without a language model) as follows:
37
+
38
+ ```python
39
+ import torch
40
+ import torchaudio
41
+ from datasets import load_dataset
42
+ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
43
+
44
+ test_dataset = load_dataset("common_voice", "or", split="test[:2%]")
45
+ processor = Wav2Vec2Processor.from_pretrained("theainerd/wav2vec2-large-xlsr-53-odia")
46
+ model = Wav2Vec2ForCTC.from_pretrained("theainerd/wav2vec2-large-xlsr-53-odia")
47
+ resampler = torchaudio.transforms.Resample(48_000, 16_000)
48
+
49
+ # Preprocessing the datasets.
50
+ # We need to read the aduio files as arrays
51
+ def speech_file_to_array_fn(batch):
52
+ speech_array, sampling_rate = torchaudio.load(batch["path"])
53
+ batch["speech"] = resampler(speech_array).squeeze().numpy()
54
+ return batch
55
+
56
+ test_dataset = test_dataset.map(speech_file_to_array_fn)
57
+ inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
58
+
59
+ with torch.no_grad():
60
+ logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
61
+
62
+ predicted_ids = torch.argmax(logits, dim=-1)
63
+
64
+ print("Prediction:", processor.batch_decode(predicted_ids))
65
+ print("Reference:", test_dataset["sentence"][:2])
66
+ ```
67
+
68
+
69
+ ## Evaluation
70
+
71
+ The model can be evaluated as follows on the Odia test data of Common Voice.
72
+
73
+
74
+ ```python
75
+ import torch
76
+ import torchaudio
77
+ from datasets import load_dataset, load_metric
78
+ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
79
+ import re
80
+
81
+ test_dataset = load_dataset("common_voice", "or", split="test")
82
+ wer = load_metric("wer")
83
+
84
+ processor = Wav2Vec2Processor.from_pretrained("theainerd/wav2vec2-large-xlsr-53-odia")
85
+ model = Wav2Vec2ForCTC.from_pretrained("theainerd/wav2vec2-large-xlsr-53-odia")
86
+ model.to("cuda")
87
+
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**: 68.75 %
118
+
119
+
120
+ ## Training
121
+
122
+ The script used for training can be found [Odia ASR Fine Tuning Wav2Vec2](https://colab.research.google.com/drive/1aHpFRTxaBeNblRHAtYOy0hBeXbbMWtot?usp=sharing)