cahya commited on
Commit
856c37a
1 Parent(s): 37ed1b9

add first commit

Browse files
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: br
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: XLSR Wav2Vec2 Indonesian by Cahya
15
+ results:
16
+ - task:
17
+ name: Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: Common Voice br
21
+ type: common_voice
22
+ args: br
23
+ metrics:
24
+ - name: Test WER
25
+ type: wer
26
+ value: 41.71
27
+ ---
28
+
29
+ # Wav2Vec2-Large-XLSR-Indonesian
30
+
31
+ Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53)
32
+ on the [Breton Common Voice dataset](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
+ The model can be used directly (without a language model) as follows:
37
+ ```python
38
+ import torch
39
+ import torchaudio
40
+ from datasets import load_dataset
41
+ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
42
+
43
+ test_dataset = load_dataset("common_voice", "br", split="test[:2%]")
44
+
45
+ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-breton")
46
+ model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-breton")
47
+
48
+ resampler = torchaudio.transforms.Resample(48_000, 16_000)
49
+
50
+ # Preprocessing the datasets.
51
+ # We need to read the aduio files as arrays
52
+ def speech_file_to_array_fn(batch):
53
+ speech_array, sampling_rate = torchaudio.load(batch["path"])
54
+ batch["speech"] = resampler(speech_array).squeeze().numpy()
55
+ return batch
56
+
57
+ test_dataset = test_dataset.map(speech_file_to_array_fn)
58
+ inputs = processor(test_dataset[:2]["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
59
+
60
+ with torch.no_grad():
61
+ logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
62
+
63
+ predicted_ids = torch.argmax(logits, dim=-1)
64
+
65
+ print("Prediction:", processor.batch_decode(predicted_ids))
66
+ print("Reference:", test_dataset[:2]["sentence"])
67
+ ```
68
+
69
+
70
+ ## Evaluation
71
+
72
+ The model can be evaluated as follows on the Indonesian test data of Common Voice.
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", "br", split="test")
82
+ wer = load_metric("wer")
83
+
84
+ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-breton")
85
+ model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-breton")
86
+ model.to("cuda")
87
+
88
+ chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\'\”\�]'
89
+
90
+ resampler = torchaudio.transforms.Resample(48_000, 16_000)
91
+
92
+ # Preprocessing the datasets.
93
+ # We need to read the aduio files as arrays
94
+ def speech_file_to_array_fn(batch):
95
+ batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
96
+ speech_array, sampling_rate = torchaudio.load(batch["path"])
97
+ batch["speech"] = resampler(speech_array).squeeze().numpy()
98
+ return batch
99
+
100
+ test_dataset = test_dataset.map(speech_file_to_array_fn)
101
+
102
+ # Preprocessing the datasets.
103
+ # We need to read the aduio files as arrays
104
+ def evaluate(batch):
105
+ inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
106
+
107
+ with torch.no_grad():
108
+ logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
109
+
110
+ pred_ids = torch.argmax(logits, dim=-1)
111
+ batch["pred_strings"] = processor.batch_decode(pred_ids)
112
+ return batch
113
+
114
+ result = test_dataset.map(evaluate, batched=True, batch_size=8)
115
+
116
+ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
117
+ ```
118
+
119
+ **Test Result**: 41.71 %
120
+
121
+ ## Training
122
+
123
+ The Common Voice `train`, `validation`, and ... datasets were used for training as well as ... and ... # TODO
124
+
125
+ The script used for training can be found [here](https://github.com/cahya-wirawan/indonesian-speech-recognition)
126
+ (will be available soon)
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "conv_bias": true,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "mean",
39
+ "ctc_zero_infinity": false,
40
+ "do_stable_layer_norm": true,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_dropout": 0.0,
44
+ "feat_extract_norm": "layer",
45
+ "feat_proj_dropout": 0.0,
46
+ "final_dropout": 0.0,
47
+ "gradient_checkpointing": true,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 1024,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.05,
55
+ "mask_channel_length": 10,
56
+ "mask_channel_min_space": 1,
57
+ "mask_channel_other": 0.0,
58
+ "mask_channel_prob": 0.0,
59
+ "mask_channel_selection": "static",
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_space": 1,
64
+ "mask_time_other": 0.0,
65
+ "mask_time_prob": 0.4,
66
+ "mask_time_selection": "static",
67
+ "model_type": "wav2vec2",
68
+ "num_attention_heads": 16,
69
+ "num_conv_pos_embedding_groups": 16,
70
+ "num_conv_pos_embeddings": 128,
71
+ "num_feat_extract_layers": 7,
72
+ "num_hidden_layers": 24,
73
+ "pad_token_id": 41,
74
+ "transformers_version": "4.4.0",
75
+ "vocab_size": 42
76
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_size": 1,
4
+ "padding_side": "right",
5
+ "padding_value": 0.0,
6
+ "return_attention_mask": true,
7
+ "sampling_rate": 16000
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48e6bbeae5990c635cc3b47956ae77479388d3c2b37db683e4563d608b8bbf5
3
+ size 1262106007
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}
vocab.json ADDED
@@ -0,0 +1 @@
 
1
+ {"w": 0, "j": 1, "h": 2, "i": 3, "v": 4, "ñ": 5, "à": 6, "u": 7, "d": 8, "ô": 9, "m": 10, "p": 11, "s": 12, "l": 13, "e": 14, "y": 16, "n": 17, "o": 18, "z": 19, "f": 20, "ê": 21, "c": 22, "ç": 23, "g": 24, "a": 25, "-": 26, "ü": 27, "r": 28, "x": 29, "'": 30, "û": 31, "b": 32, "é": 33, "è": 34, "q": 35, "k": 36, "ù": 37, "â": 38, "t": 39, "|": 15, "[UNK]": 40, "[PAD]": 41}