Training in progress, step 500

.ipynb_checkpoints/preprocessor_config-checkpoint.json

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

.ipynb_checkpoints/train_results-checkpoint.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "train_loss": 1.5738848333155855,
+    "train_runtime": 24806.553,
+    "train_samples": 6034,
+    "train_samples_per_second": 12.162,
+    "train_steps_per_second": 0.379
+}

.ipynb_checkpoints/vocab-checkpoint.json

@@ -0,0 +1 @@
+{"،": 1, "؛": 2, "؟": 3, "ئ": 4, "ا": 5, "ب": 6, "ت": 7, "ج": 8, "خ": 9, "د": 10, "ر": 11, "ز": 12, "س": 13, "ش": 14, "غ": 15, "ف": 16, "ق": 17, "ك": 18, "ل": 19, "م": 20, "ن": 21, "و": 22, "ى": 23, "ي": 24, "پ": 25, "چ": 26, "ژ": 27, "ڭ": 28, "گ": 29, "ھ": 30, "ۆ": 31, "ۇ": 32, "ۈ": 33, "ۋ": 34, "ې": 35, "ە": 36, "‹": 37, "›": 38, "−": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 42, "</s>": 43}

config.json

@@ -76,7 +76,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 43,
+  "pad_token_id": 41,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -102,6 +102,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.16.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 46,
+  "vocab_size": 44,
   "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07b4dd396459cd0f012358a86158ae1d7b371ce3ae2cbc67f4c43b9694dbd2c
-size 1262112241
+oid sha256:229d18875aa5551d40c74956fa68d813fbb0cdcf4e488137e895d56fefa1cae6
+size 1262104049

runs/Jan28_17-40-32_job-0074bb36-c67f-4775-b1b6-176eb09b0ba4/1643391738.2800581/events.out.tfevents.1643391738.job-0074bb36-c67f-4775-b1b6-176eb09b0ba4.843454.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b097f29a6bc269d898423d71c69267f61a1dfe37e41799508bb02ded928bd248
+size 4802

runs/Jan28_17-40-32_job-0074bb36-c67f-4775-b1b6-176eb09b0ba4/events.out.tfevents.1643391738.job-0074bb36-c67f-4775-b1b6-176eb09b0ba4.843454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fbd8a92cb461a252a5c5c12c6026b6848e17b94dd2ed6e80d159342e221a5a
+size 5830

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}]}

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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./xls-r-uyghur-cv8", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe6fb2dd05183df014db8cb29e4ad8e2e591ee22daf75668bad7cff7aa510d7
+oid sha256:81c852d75cc7308b223dd2f8668f73ae311d16d0fb416266206ec9a8c702837a
 size 3055

vocab.json

@@ -0,0 +1 @@
+{"،": 1, "؛": 2, "؟": 3, "ئ": 4, "ا": 5, "ب": 6, "ت": 7, "ج": 8, "خ": 9, "د": 10, "ر": 11, "ز": 12, "س": 13, "ش": 14, "غ": 15, "ف": 16, "ق": 17, "ك": 18, "ل": 19, "م": 20, "ن": 21, "و": 22, "ى": 23, "ي": 24, "پ": 25, "چ": 26, "ژ": 27, "ڭ": 28, "گ": 29, "ھ": 30, "ۆ": 31, "ۇ": 32, "ۈ": 33, "ۋ": 34, "ې": 35, "ە": 36, "‹": 37, "›": 38, "−": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}