aismlv commited on
Commit
0895b1b
1 Parent(s): 83740f3

Add model card

Browse files
Files changed (1) hide show
  1. README.md +126 -0
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: ky
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: {Wav2Vec2-XLSR-53 Kyrgyz by adilism}
15
+ results:
16
+ - task:
17
+ name: Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: Common Voice ky
21
+ type: common_voice
22
+ args: ky
23
+ metrics:
24
+ - name: Test WER
25
+ type: wer
26
+ value: 34.08
27
+ ---
28
+
29
+ # Wav2Vec2-Large-XLSR-53-Kyrgyz
30
+
31
+ Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Kyrgyz using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset.
32
+
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", "ky", split="test[:2%]")
46
+
47
+ processor = Wav2Vec2Processor.from_pretrained("adilism/wav2vec2-large-xlsr-kyrgyz")
48
+ model = Wav2Vec2ForCTC.from_pretrained("adilism/wav2vec2-large-xlsr-kyrgyz")
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
+ speech_array, sampling_rate = torchaudio.load(batch["path"])
56
+ batch["speech"] = resampler(speech_array).squeeze().numpy()
57
+ return 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
+ logits = 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 Kyrgyz 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", "ky", split="test")
85
+ wer = load_metric("wer")
86
+
87
+ processor = Wav2Vec2Processor.from_pretrained("adilism/wav2vec2-large-xlsr-kyrgyz")
88
+ model = Wav2Vec2ForCTC.from_pretrained("adilism/wav2vec2-large-xlsr-kyrgyz")
89
+ model.to("cuda")
90
+
91
+ chars_to_ignore = [",", "?", ".", "!", "-", ";", ":", "—", "–", "”"]
92
+ chars_to_ignore_regex = f'[{"".join(chars_to_ignore)}]'
93
+ resampler = torchaudio.transforms.Resample(48_000, 16_000)
94
+
95
+ # Preprocessing the datasets.
96
+ # We need to read the aduio files as arrays
97
+ def speech_file_to_array_fn(batch):
98
+ batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
99
+ speech_array, sampling_rate = torchaudio.load(batch["path"])
100
+ batch["speech"] = resampler(speech_array).squeeze().numpy()
101
+ return batch
102
+
103
+ test_dataset = test_dataset.map(speech_file_to_array_fn)
104
+
105
+ # Preprocessing the datasets.
106
+ # We need to read the aduio files as arrays
107
+ def evaluate(batch):
108
+ inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
109
+
110
+ with torch.no_grad():
111
+ logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
112
+
113
+ pred_ids = torch.argmax(logits, dim=-1)
114
+ batch["pred_strings"] = processor.batch_decode(pred_ids)
115
+ return batch
116
+
117
+ result = test_dataset.map(evaluate, batched=True, batch_size=8)
118
+
119
+ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
120
+ ```
121
+
122
+ **Test Result**: 34.08 %
123
+
124
+ ## Training
125
+
126
+ The Common Voice `train` and `validation` datasets were used for training.