patrickvonplaten commited on
Commit
3fcd3d1
1 Parent(s): 25b4b75

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +125 -1
README.md CHANGED
@@ -1 +1,125 @@
1
- hello
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: fi
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 Finnish by Birger Moell
13
+ results:
14
+ - task:
15
+ name: Speech Recognition
16
+ type: automatic-speech-recognition
17
+ dataset:
18
+ name: Common Voice fi
19
+ type: common_voice
20
+ args: fi
21
+ metrics:
22
+ - name: Test WER
23
+ type: wer
24
+ value: ???
25
+ ---
26
+
27
+ # Wav2Vec2-Large-XLSR-53-Hungarian
28
+
29
+ Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Finnish 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
+
32
+ ## Usage
33
+
34
+ The model can be used directly (without a language model) as follows:
35
+
36
+ ```python
37
+ import torch
38
+ import torchaudio
39
+ from datasets import load_dataset
40
+ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
41
+
42
+ test_dataset = load_dataset("common_voice", "fi", split="test[:2%]").
43
+
44
+ processor = Wav2Vec2Processor.from_pretrained("birgermoell/wav2vec2-large-xlsr-finnish")
45
+ model = Wav2Vec2ForCTC.from_pretrained("birgermoell/wav2vec2-large-xlsr-finnish")
46
+
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 Finnish 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", "fi", split="test")
82
+ wer = load_metric("wer")
83
+
84
+ processor = Wav2Vec2Processor.from_pretrained("birgermoell/wav2vec2-large-xlsr-finnish")
85
+ model = Wav2Vec2ForCTC.from_pretrained("birgermoell/wav2vec2-large-xlsr-finnish")
86
+ model.to("cuda")
87
+
88
+ chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
89
+ resampler = torchaudio.transforms.Resample(48_000, 16_000)
90
+
91
+ # Preprocessing the datasets.
92
+ # We need to read the aduio files as arrays
93
+ def speech_file_to_array_fn(batch):
94
+ batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
95
+ speech_array, sampling_rate = torchaudio.load(batch["path"])
96
+ batch["speech"] = resampler(speech_array).squeeze().numpy()
97
+ return batch
98
+
99
+ test_dataset = test_dataset.map(speech_file_to_array_fn)
100
+
101
+ # Preprocessing the datasets.
102
+ # We need to read the aduio files as arrays
103
+ def evaluate(batch):
104
+ inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
105
+
106
+ with torch.no_grad():
107
+ logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
108
+ pred_ids = torch.argmax(logits, dim=-1)
109
+
110
+ batch["pred_strings"] = processor.batch_decode(pred_ids)
111
+ return batch
112
+
113
+ result = test_dataset.map(evaluate, batched=True, batch_size=8)
114
+
115
+ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
116
+ ```
117
+
118
+ **Test Result**: ???
119
+
120
+
121
+ ## Training
122
+
123
+ The Common Voice `train` and `validation` datasets were used for training.
124
+ The script used for training can be found ???
125
+