add files

README.md

@@ -0,0 +1,19 @@
+---
+language: hr
+tags:
+- audio
+- automatic-speech-recognition
+- voxpopuli
+license: cc-by-nc-4.0
+---
+
+# Wav2Vec2-Base-VoxPopuli-Finetuned
+
+[Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) large model pretrained on the 10K unlabeled subset of [VoxPopuli corpus](https://arxiv.org/abs/2101.00390) and fine-tuned on the transcribed data in hr (refer to Table 1 of paper for more information).
+
+**Paper**: *[VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation
+Learning, Semi-Supervised Learning and Interpretation](https://arxiv.org/abs/2101.00390)*
+
+**Authors**: *Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux* from *Facebook AI*
+
+See the official website for more information, [here](https://github.com/facebookresearch/voxpopuli/)

config.json

@@ -0,0 +1,68 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "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,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "transformers_version": "4.6.0.dev0",
+  "vocab_size": 39
+}

preprocessor_config.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5286a501690dd24494e3e3d18e83f47f30d3fec0c7104798d5bcc9dbcebc946
+size 377694060

special_tokens_map.json

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

tokenizer_config.json

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

vocab.json

@@ -0,0 +1 @@
+{"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "a": 5, "i": 6, "o": 7, "e": 8, "n": 9, "r": 10, "j": 11, "t": 12, "s": 13, "u": 14, "m": 15, "v": 16, "d": 17, "k": 18, "p": 19, "l": 20, "z": 21, "g": 22, "b": 23, "c": 24, "h": 25, "č": 26, "š": 27, "ž": 28, "ć": 29, "f": 30, "đ": 31, "w": 32, "y": 33, "x": 34, "q": 35, "ü": 36, "á": 37, "ö": 38}