F

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,47 @@
----
-license: mit
----
+HEAD
+---
+license: mit
+---
+
+---
+language:
+- multilingual
+license: apache-2.0
+tags:
+- voice
+- classification
+- vocalization
+- speech
+- audio
+datasets:
+- NonverbalVocalization
+widget:
+- src: >-
+    https://huggingface.co/padmalcom/wav2vec2-large-nonverbalvocalization-classification/resolve/main/test.wav
+  example_title: Sample 1
+pipeline_tag: audio-classification
+metrics:
+- accuracy
+---
+This language indendent wav2vec2 classification model is based on [this dataset](https://github.com/deeplyinc/Nonverbal-Vocalization-Dataset).
+
+Sound classes are:
+- teeth-chattering
+- teeth-grinding
+- tongue-clicking
+- nose-blowing
+- coughing
+- yawning
+- throat clearing
+- sighing
+- lip-popping
+- lip-smacking
+- panting
+- crying
+- laughing
+- sneezing
+- moaning
+- screaming
+
+*inference.py* shows, how the model can be used.
+18e5a42 (Initial commit of Nonverbal-AudioCLwav2vec2 model)

config.json

@@ -0,0 +1,148 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-960h-lv60-self",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSpeechClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "finetuning_task": "wav2vec2_clf",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "teeth-chattering",
+    "1": "teeth-grinding",
+    "2": "tongue-clicking",
+    "3": "nose-blowing",
+    "4": "coughing",
+    "5": "yawning",
+    "6": "throat-clearing",
+    "7": "sighing",
+    "8": "lip-popping",
+    "9": "lip-smacking",
+    "10": "panting",
+    "11": "crying",
+    "12": "laughing",
+    "13": "sneezing",
+    "14": "moaning",
+    "15": "screaming"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "coughing": 4,
+    "crying": 11,
+    "laughing": 12,
+    "lip-popping": 8,
+    "lip-smacking": 9,
+    "moaning": 14,
+    "nose-blowing": 3,
+    "panting": 10,
+    "screaming": 15,
+    "sighing": 7,
+    "sneezing": 13,
+    "teeth-chattering": 0,
+    "teeth-grinding": 1,
+    "throat-clearing": 6,
+    "tongue-clicking": 2,
+    "yawning": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

inference.py

@@ -0,0 +1,39 @@
+import torch
+import torch.nn.functional as F
+import torchaudio
+from transformers import AutoConfig, Wav2Vec2Processor
+
+from Wav2Vec2ForSpeechClassification import Wav2Vec2ForSpeechClassification
+
+MY_MODEL = "padmalcom/wav2vec2-large-nonverbalvocalization-classification"
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+config = AutoConfig.from_pretrained(MY_MODEL)
+processor = Wav2Vec2Processor.from_pretrained(MY_MODEL)
+sampling_rate = processor.feature_extractor.sampling_rate
+model = Wav2Vec2ForSpeechClassification.from_pretrained(MY_MODEL).to(device)
+
+def speech_file_to_array_fn(path, sampling_rate):
+	speech_array, _sampling_rate = torchaudio.load(path)
+	resampler = torchaudio.transforms.Resample(_sampling_rate)
+	speech = resampler(speech_array).squeeze().numpy()
+	return speech
+
+
+def predict(path, sampling_rate):
+	speech = speech_file_to_array_fn(path, sampling_rate)
+	features = processor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
+	
+	input_values = features.input_values.to(device)
+	attention_mask = features.attention_mask.to(device)
+
+	with torch.no_grad():
+		logits = model(input_values, attention_mask=attention_mask).logits
+
+	scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
+	outputs = [{"Vocalization": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
+	return outputs
+	
+res = predict("test.wav", 16000)
+max = max(res, key=lambda x: x['Score'])
+print("Expected lip popping:", max)

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a09bf8bb4a628bdf32d6d96d37e15c9b3f490bda8f48c08441f5cb258e28e9
+size 1266163373

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "do_normalize": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "facebook/wav2vec2-large-960h-lv60-self",
+  "pad_token": "<pad>",
+  "replace_word_delimiter_char": " ",
+  "return_attention_mask": true,
+  "special_tokens_map_file": "C:\\Users\\admin/.cache\\huggingface\\hub\\models--facebook--wav2vec2-large-960h-lv60-self\\snapshots\\54074b1c16f4de6a5ad59affb4caa8f2ea03a119\\special_tokens_map.json",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19e5d57926cf4a2a3707f9b4f4871fcffe80b7405debaf0f3eb903f056575dd
+size 3375

vocab.json

@@ -0,0 +1,34 @@
+{
+  "'": 27,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "A": 7,
+  "B": 24,
+  "C": 19,
+  "D": 14,
+  "E": 5,
+  "F": 20,
+  "G": 21,
+  "H": 11,
+  "I": 10,
+  "J": 29,
+  "K": 26,
+  "L": 15,
+  "M": 17,
+  "N": 9,
+  "O": 8,
+  "P": 23,
+  "Q": 30,
+  "R": 13,
+  "S": 12,
+  "T": 6,
+  "U": 16,
+  "V": 25,
+  "W": 18,
+  "X": 28,
+  "Y": 22,
+  "Z": 31,
+  "|": 4
+}