Init

.gitattributes

@@ -1,3 +1,4 @@
+*.txt filter=lfs diff=lfs merge=lfs -text
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,45 @@
 ---
-license: apache-2.0
+language: 
+  - uk
+license: "apache-2.0"
+datasets:
+- mozilla-foundation/common_voice_7_0
 ---
+
+Has aphostrophes and hyphens.
+
+The language model is 3-gram.
+
+Attribution to the dataset of Language Model:
+
+Chaplynskyi, D. et al. (2021) lang-uk Ukrainian Ubercorpus [Data set]. https://lang.org.ua/uk/corpora/#anchor4
+
+
+Metrics:
+
+Without LM:
+
+- WER: 0.2933
+- CER: 0.0539
+
+---
+
+News LM (this repository):
+
+- WER: 0.1562
+- CER: 0.0328
+
+
+SMALL LM (https://huggingface.co/Yehor/wav2vec2-xls-r-300m-uk-with-small-lm):
+
+- WER: 0.1674
+- CER: 0.0332
+ 
+Wiki LM (https://huggingface.co/Yehor/wav2vec2-xls-r-300m-uk-with-wiki-lm):
+
+- WER: 0.1526
+- CER: 0.0307
+
+---
+
+Join Ukrainian Speech Recognition Community - https://t.me/speech_recognition_uk

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 37, "</s>": 38}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "\u0430", "\u0431", "\u0432", "\u0433", "\u0434", "\u0435", "\u0436", "\u0437", "\u0438", "\u0439", "\u043a", "\u043b", "\u043c", "\u043d", "\u043e", "\u043f", "\u0440", "\u0441", "\u0442", "\u0443", "\u0444", "\u0445", "\u0446", "\u0447", "\u0448", "\u0449", "\u044c", "\u044e", "\u044f", "\u0454", "\u0456", "\u0457", "'", "-", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "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": "mean",
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.04,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "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": 36,
+  "proj_codevector_dim": 768,
+  "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": "4.20.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 39,
+  "xvector_output_dim": 512
+}

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/news_3gram_correct.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8959e5cb45e64e5ffd65f71ef072474f539f1a1d5cbdd3fc73f33e7ae87a61e2
+size 8890488797

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a06b1b9e1cc02693410c354bd257ef809f39350955908dba1b64d8b1b081148
+size 63445099

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b618404ca0a65d2e3cc80eaa58de06663ed98986395485c918ef5acc23c2bca1
+size 1262058609

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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": "|", "replace_word_delimiter_char": " ", "name_or_path": "Yehor/wav2vec2-xls-r-300m-uk-with-small-lm", "processor_class": "Wav2Vec2ProcessorWithLM", "special_tokens_map_file": null, "trust_remote_code": false, "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"'": 33, "-": 34, "[PAD]": 36, "[UNK]": 35, "|": 0, "а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "е": 6, "ж": 7, "з": 8, "и": 9, "й": 10, "к": 11, "л": 12, "м": 13, "н": 14, "о": 15, "п": 16, "р": 17, "с": 18, "т": 19, "у": 20, "ф": 21, "х": 22, "ц": 23, "ч": 24, "ш": 25, "щ": 26, "ь": 27, "ю": 28, "я": 29, "є": 30, "і": 31, "ї": 32}