Training in progress, step 93

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 36,
+  "<s>": 35
+}

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.9523809523809526,
+    "eval_loss": 3.9626145362854004,
+    "eval_runtime": 14.7624,
+    "eval_samples_per_second": 16.867,
+    "eval_steps_per_second": 2.168,
+    "eval_wer": 1.0,
     "total_flos": 5.949146211248116e+17,
     "train_loss": 10.376545229265767,
     "train_runtime": 223.9196,

config.json

@@ -86,7 +86,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 34,
+  "pad_token_id": 30,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -112,6 +112,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.43.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 37,
+  "vocab_size": 33,
   "xvector_output_dim": 512
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9523809523809526,
+    "eval_loss": 3.9626145362854004,
+    "eval_runtime": 14.7624,
+    "eval_samples_per_second": 16.867,
+    "eval_steps_per_second": 2.168,
+    "eval_wer": 1.0
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d76a24b1745fd24545f386a59a53d15b488a195061a64adf61df68cceae69b9
-size 1261959180
+oid sha256:54a7b4ce47f0d519702ae128ca9e7ee985cdbd1158fa0008c25f8c8ebf8e789e
+size 1261942780

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 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "33": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624c975b502cb3434bd0951684de7207181322d2cca3b8d621c864c15e38316f
+oid sha256:57ec0e8cbf2a45869b2210c4ce89254cf7fed486539acc39f84650fcfd0059b6
 size 5304

vocab.json

@@ -0,0 +1,37 @@
+{
+  "[PAD]": 34,
+  "[UNK]": 33,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "|": 0,
+  "á": 27,
+  "í": 28,
+  "ř": 29,
+  "ž": 30,
+  "—": 31,
+  "’": 32
+}