cahya commited on
Commit
e399bd4
1 Parent(s): de8589e

add the model

Browse files
Files changed (3) hide show
  1. README.md +126 -0
  2. config.json +67 -0
  3. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: tr
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 Base Turkish by Cahya
15
+ results:
16
+ - task:
17
+ name: Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: Common Voice tr
21
+ type: common_voice
22
+ args: tr
23
+ metrics:
24
+ - name: Test WER
25
+ type: wer
26
+ value: 13.70
27
+ ---
28
+
29
+ # Wav2Vec2-Large-XLSR-Turkish
30
+
31
+ This is the model for Wav2Vec2-Base-Turkish-Artificial-CV, a fine-tuned
32
+ [cahya/wav2vec2-base-turkish-artificial](https://huggingface.co/cahya/wav2vec2-base-turkish-artificial)
33
+ model on [Turkish Common Voice dataset](https://huggingface.co/datasets/common_voice).
34
+
35
+ When using this model, make sure that your speech input is sampled at 16kHz.
36
+
37
+ ## Usage
38
+ The model can be used directly (without a language model) as follows:
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", "tr", split="test[:2%]")
46
+
47
+ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-base-turkish-artificial-cv")
48
+ model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-base-turkish-artificial-cv")
49
+
50
+
51
+ # Preprocessing the datasets.
52
+ # We need to read the aduio files as arrays
53
+ def speech_file_to_array_fn(batch):
54
+ speech_array, sampling_rate = torchaudio.load(batch["path"])
55
+ resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
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[:2]["speech"], 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[:2]["sentence"])
69
+ ```
70
+
71
+
72
+ ## Evaluation
73
+
74
+ The model can be evaluated as follows on the Turkish test data of Common Voice.
75
+
76
+ ```python
77
+ import torch
78
+ import torchaudio
79
+ from datasets import load_dataset, load_metric
80
+ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
81
+ import re
82
+
83
+ test_dataset = load_dataset("common_voice", "tr", split="test")
84
+ wer = load_metric("wer")
85
+
86
+ processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-base-turkish-artificial-cv")
87
+ model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-base-turkish-artificial-cv")
88
+ model.to("cuda")
89
+
90
+ chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\‘\”\'\`…\’»«]'
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
+ resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
98
+ batch["speech"] = resampler(speech_array).squeeze().numpy()
99
+ return batch
100
+
101
+ test_dataset = test_dataset.map(speech_file_to_array_fn)
102
+
103
+ # Preprocessing the datasets.
104
+ # We need to read the aduio files as arrays
105
+ def evaluate(batch):
106
+ inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
107
+
108
+ with torch.no_grad():
109
+ logits = model(inputs.input_values.to("cuda")).logits
110
+
111
+ pred_ids = torch.argmax(logits, dim=-1)
112
+ batch["pred_strings"] = processor.batch_decode(pred_ids)
113
+ return batch
114
+
115
+ result = test_dataset.map(evaluate, batched=True, batch_size=8)
116
+
117
+ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
118
+ ```
119
+
120
+ **Test Result**: 13.70 %
121
+
122
+ ## Training
123
+
124
+ The Common Voice `train`, `validation`, other and invalidated
125
+
126
+ The script used for training can be found [here](https://github.com/cahya-wirawan/indonesian-speech-recognition)
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/models/wav2vec2-base-turkish-artificial",
3
+ "activation_dropout": 0.055,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.094,
9
+ "bos_token_id": 1,
10
+ "conv_bias": false,
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": true,
40
+ "do_stable_layer_norm": false,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_norm": "group",
44
+ "feat_proj_dropout": 0.04,
45
+ "final_dropout": 0.1,
46
+ "gradient_checkpointing": true,
47
+ "hidden_act": "gelu",
48
+ "hidden_dropout": 0.047,
49
+ "hidden_size": 768,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 3072,
52
+ "layer_norm_eps": 1e-05,
53
+ "layerdrop": 0.041,
54
+ "mask_feature_length": 10,
55
+ "mask_feature_prob": 0.0,
56
+ "mask_time_length": 10,
57
+ "mask_time_prob": 0.4,
58
+ "model_type": "wav2vec2",
59
+ "num_attention_heads": 12,
60
+ "num_conv_pos_embedding_groups": 16,
61
+ "num_conv_pos_embeddings": 128,
62
+ "num_feat_extract_layers": 7,
63
+ "num_hidden_layers": 12,
64
+ "pad_token_id": 39,
65
+ "transformers_version": "4.5.0.dev0",
66
+ "vocab_size": 40
67
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c26dc555652924053d8702dadd345b7bbb2f43402b4983283e75c9983445541
3
+ size 377700076