update model

README.md

@@ -24,10 +24,10 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 11.17
+         value: 14.33
        - name: Test CER
          type: cer
-         value: 2.87
+         value: 3.36
 ---
 
 # Wav2Vec2-Large-XLSR-53-Polish
@@ -81,11 +81,16 @@ for i, predicted_sentence in enumerate(predicted_sentences):
 
 | Reference  | Prediction |
 | ------------- | ------------- |
-| """CZY DRZWI BYŁY ZAMKNIĘTE?""" | CZY DRZWI BYŁY ZAMKNIĘTE |
-| GDZIEŻ TU POWÓD DO WYRZUTÓW? | GDZIEŻ TO POWÓD DO WYŻYTÓW |
-| """O TEM JEDNAK NIE BYŁO MOWY.""" | O TEM JEDNAK NIE BYŁO MOWY N |
-| LUBIĘ GO. | LUBIĘ GO |
-| — TO MI NIE POMAGA. | TO MI NIE POMAGA |
+| """CZY DRZWI BYŁY ZAMKNIĘTE?""" | PRZY DRZWI BYŁY ZAMKNIĘTE |
+| GDZIEŻ TU POWÓD DO WYRZUTÓW? | WGDZIEŻ TO POM DO WYRYDÓ |
+| """O TEM JEDNAK NIE BYŁO MOWY.""" | O TEM JEDNAK NIE BYŁO MOWY |
+| LUBIĘ GO. | LUBIĄ GO |
+| — TO MI NIE POMAGA. | TO MNIE NIE POMAGA |
+| WCIĄŻ LUDZIE WYSIADAJĄ PRZED ZAMKIEM, Z MIASTA, Z PRAGI. | WCIĄŻ LUDZIE WYSIADAJĄ PRZED ZAMKIEM Z MIASTA Z PRAGI |
+| ALE ON WCALE INACZEJ NIE MYŚLAŁ. | ONY MONITCENIE PONACZUŁA NA MASU |
+| A WY, CO TAK STOICIE? | A WY CO TAK STOICIE |
+| A TEN PRZYRZĄD DO CZEGO SŁUŻY? | A TEN PRZYRZĄD DO CZEGO SŁUŻY |
+| NA JUTRZEJSZYM KOLOKWIUM BĘDZIE PIĘĆ PYTAŃ OTWARTYCH I TEST WIELOKROTNEGO WYBORU. | NAJUTRZEJSZYM KOLOKWIUM BĘDZIE PIĘĆ PYTAŃ OTWARTYCH I TEST WIELOKROTNEGO WYBORU |
 
 ## Evaluation
 
@@ -102,9 +107,11 @@ LANG_ID = "pl"
 MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-polish"
 DEVICE = "cuda"
 
-CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞", 
+CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
                    "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
-                   "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。"]
+                   "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
+                   "、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
+                   "『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]
 
 test_dataset = load_dataset("common_voice", LANG_ID, split="test")
 
@@ -156,7 +163,7 @@ In the table below I report the Word Error Rate (WER) and the Character Error Ra
 
 | Model | WER | CER |
 | ------------- | ------------- | ------------- |
-| jonatasgrosman/wav2vec2-large-xlsr-53-polish | **11.17%** | **2.87%** |
+| jonatasgrosman/wav2vec2-large-xlsr-53-polish | **14.33%** | **3.36%** |
 | facebook/wav2vec2-large-xlsr-53-polish | 20.17% | 5.38% |
 | alexcleu/wav2vec2-large-xlsr-polish | 21.72% | 5.17% |
 | mbien/wav2vec2-large-xlsr-polish | 22.93% | 5.13% |

config.json

@@ -7,6 +7,8 @@
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
   "conv_bias": true,
   "conv_dim": [
     512,
@@ -37,12 +39,14 @@
   ],
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": true,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "gradient_checkpointing": true,
   "hidden_act": "gelu",
@@ -66,11 +70,15 @@
   "mask_time_selection": "static",
   "model_type": "wav2vec2",
   "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,
   "pad_token_id": 0,
-  "transformers_version": "4.5.0.dev0",
-  "vocab_size": 42
+  "proj_codevector_dim": 768,
+  "transformers_version": "4.7.0.dev0",
+  "vocab_size": 40
 }

preprocessor_config.json

@@ -1,5 +1,6 @@
 {
   "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:411ade8d442a8d084db3c0cc0f30ac40b38b16debf49ea835400a3a121fec6fb
-size 1262106007
+oid sha256:1bd2a29f3b6093cc7a0f9ad39d56b5b11ae00f588878035e117e379dd3c204a6
+size 1262097815

vocab.json

@@ -1 +1 @@
-{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "A": 5, "I": 6, "E": 7, "O": 8, "Z": 9, "N": 10, "S": 11, "W": 12, "R": 13, "C": 14, "Y": 15, "M": 16, "T": 17, "D": 18, "K": 19, "P": 20, "Ł": 21, "J": 22, "U": 23, "L": 24, "B": 25, "Ę": 26, "G": 27, "Ą": 28, "Ż": 29, "H": 30, "Ś": 31, "Ó": 32, "Ć": 33, "F": 34, "Ń": 35, "Ź": 36, "V": 37, "-": 38, "Q": 39, "X": 40, "'": 41}
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "-": 5, "A": 6, "B": 7, "C": 8, "D": 9, "E": 10, "F": 11, "G": 12, "H": 13, "I": 14, "J": 15, "K": 16, "L": 17, "M": 18, "N": 19, "O": 20, "P": 21, "R": 22, "S": 23, "T": 24, "U": 25, "V": 26, "W": 27, "X": 28, "Y": 29, "Z": 30, "Ó": 31, "Ą": 32, "Ć": 33, "Ę": 34, "Ł": 35, "Ń": 36, "Ś": 37, "Ź": 38, "Ż": 39}