muratsimsek003/wav2vec2-base-turkish-istech

.gitattributes

@@ -1,35 +1,9 @@
-*.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
+checkpoint-3/model.safetensors filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-3/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-3/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-3/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-3/training_args.bin filter=lfs diff=lfs merge=lfs -text
+runs/Aug08_13-24-06_71988beecfdf/events.out.tfevents.1723123450.71988beecfdf.1537.0 filter=lfs diff=lfs merge=lfs -text
+runs/Aug08_13-24-06_71988beecfdf/events.out.tfevents.1723123483.71988beecfdf.1537.1 filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,18 +1,18 @@
 ---
+license: apache-2.0
 base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
 datasets:
 - common_voice_6_1
-license: apache-2.0
 metrics:
 - wer
-tags:
-- generated_from_trainer
 model-index:
 - name: wav2vec2-base-turkish-istech
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: common_voice_6_1
       type: common_voice_6_1
@@ -20,9 +20,9 @@ model-index:
       split: train[:10%]
       args: tr
     metrics:
-    - type: wer
+    - name: Wer
+      type: wer
       value: 1.0105162523900573
-      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": false,
   "sampling_rate": 16000
 }

runs/Aug08_13-24-06_71988beecfdf/events.out.tfevents.1723123483.71988beecfdf.1537.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf5b7d72a1054d64116a683d7736996713109150431d90a75c434716e5ae104
-size 712
+oid sha256:b5cde60e03ae4c652b197b4d7ee3e4ec77be3921e8a572fc2a8a8568cfa284f4
+size 1024

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 +1,50 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "do_normalize": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "return_attention_mask": false,
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

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
+}