End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: facebook/wav2vec2-xls-r-300m
+base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
 metrics:
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5326
-- Wer: 0.7415
-- Cer: 0.2170
+- Loss: 3.6245
+- Wer: 1.0
+- Cer: 1.0
 
 ## Model description
 
@@ -39,40 +39,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 32
-- eval_batch_size: 16
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1000
-- num_epochs: 100
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step  | Validation Loss | Wer    | Cer    |
-|:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
-| 7.5237        | 4.9751  | 1000  | 3.8439          | 1.0    | 1.0    |
-| 2.6634        | 9.9502  | 2000  | 1.3226          | 0.9684 | 0.3816 |
-| 1.4289        | 14.9254 | 3000  | 1.0885          | 0.9007 | 0.2868 |
-| 1.1709        | 19.9005 | 4000  | 1.0005          | 0.8495 | 0.2609 |
-| 1.0088        | 24.8756 | 5000  | 1.0035          | 0.8149 | 0.2409 |
-| 0.8933        | 29.8507 | 6000  | 1.0224          | 0.8326 | 0.2442 |
-| 0.7856        | 34.8259 | 7000  | 1.0826          | 0.7804 | 0.2334 |
-| 0.7118        | 39.8010 | 8000  | 1.1140          | 0.7814 | 0.2331 |
-| 0.6442        | 44.7761 | 9000  | 1.1626          | 0.7857 | 0.2319 |
-| 0.5947        | 49.7512 | 10000 | 1.1976          | 0.7798 | 0.2318 |
-| 0.5439        | 54.7264 | 11000 | 1.2419          | 0.7835 | 0.2234 |
-| 0.4957        | 59.7015 | 12000 | 1.3443          | 0.7523 | 0.2220 |
-| 0.4581        | 64.6766 | 13000 | 1.3568          | 0.7704 | 0.2216 |
-| 0.4346        | 69.6517 | 14000 | 1.3921          | 0.7643 | 0.2227 |
-| 0.4044        | 74.6269 | 15000 | 1.4720          | 0.7572 | 0.2208 |
-| 0.3794        | 79.6020 | 16000 | 1.4621          | 0.7496 | 0.2189 |
-| 0.3586        | 84.5771 | 17000 | 1.4913          | 0.7460 | 0.2198 |
-| 0.3432        | 89.5522 | 18000 | 1.5223          | 0.7460 | 0.2195 |
-| 0.3219        | 94.5274 | 19000 | 1.5370          | 0.7392 | 0.2162 |
-| 0.3144        | 99.5025 | 20000 | 1.5326          | 0.7415 | 0.2170 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer | Cer |
+|:-------------:|:------:|:----:|:---------------:|:---:|:---:|
+| 5.867         | 1.9963 | 400  | 4.7211          | 1.0 | 1.0 |
+| 3.9734        | 3.9963 | 800  | 3.8661          | 1.0 | 1.0 |
+| 3.8277        | 5.9963 | 1200 | 3.8014          | 1.0 | 1.0 |
+| 3.7313        | 7.9963 | 1600 | 3.6245          | 1.0 | 1.0 |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 96,
+  "<s>": 95
+}

config.json

@@ -59,12 +59,20 @@
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
   "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
   "num_attention_heads": 16,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2720f10035ae6b5d26c97be9e232aff19fff68b1c709448957e62072647ced
+oid sha256:a938469e1f7258ad0dd72fe0579c2e5a9b70551d3ec6bb4768e50d12d1d38538
 size 1262205180

runs/Jul21_10-03-31_cs-01k0p4mp7ex7fxc1hfkvvfygh8/events.out.tfevents.1753092422.cs-01k0p4mp7ex7fxc1hfkvvfygh8.21540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8eef627e54be06da2f9d5b7e5f9991e5b47603262ba69b80260e3f6d7152c2f
+size 6772

runs/Jul21_10-15-24_cs-01k0p4mp7ex7fxc1hfkvvfygh8/events.out.tfevents.1753093122.cs-01k0p4mp7ex7fxc1hfkvvfygh8.27519.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85609f0a5a3c2e76ba319edce9ddbb3a71d6a3bdc62a9a36ef19d8efb35377cc
+size 11751

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 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "93": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "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:f1d5426dbef520593377ce881b992fdf314dfdb53ca5572bb11a31e8b1c9edb4
+oid sha256:dc78a7f8f8c20f650c4a14201b815bf3dbe9933f7d5a1fe9a9547121e8578283
 size 5304

vocab.json

@@ -0,0 +1,97 @@
+{
+  "(": 1,
+  ")": 2,
+  "/": 3,
+  "0": 4,
+  "1": 5,
+  "2": 6,
+  "3": 7,
+  "4": 8,
+  "5": 9,
+  "6": 10,
+  "7": 11,
+  "8": 12,
+  "9": 13,
+  "[PAD]": 94,
+  "[UNK]": 93,
+  "a": 14,
+  "b": 15,
+  "c": 16,
+  "e": 17,
+  "f": 18,
+  "g": 19,
+  "h": 20,
+  "i": 21,
+  "k": 22,
+  "l": 23,
+  "m": 24,
+  "n": 25,
+  "o": 26,
+  "p": 27,
+  "r": 28,
+  "s": 29,
+  "t": 30,
+  "u": 31,
+  "v": 32,
+  "w": 33,
+  "y": 34,
+  "|": 0,
+  "ค": 35,
+  "บ": 36,
+  "ย": 37,
+  "ร": 38,
+  "ั": 39,
+  "ກ": 40,
+  "ຂ": 41,
+  "ຄ": 42,
+  "ງ": 43,
+  "ຈ": 44,
+  "ຊ": 45,
+  "ຍ": 46,
+  "ດ": 47,
+  "ຕ": 48,
+  "ຖ": 49,
+  "ທ": 50,
+  "ນ": 51,
+  "ບ": 52,
+  "ປ": 53,
+  "ຜ": 54,
+  "ຝ": 55,
+  "ພ": 56,
+  "ຟ": 57,
+  "ມ": 58,
+  "ຢ": 59,
+  "ຣ": 60,
+  "ລ": 61,
+  "ວ": 62,
+  "ສ": 63,
+  "ຫ": 64,
+  "ອ": 65,
+  "ຮ": 66,
+  "ະ": 67,
+  "ັ": 68,
+  "າ": 69,
+  "ຳ": 70,
+  "ິ": 71,
+  "ີ": 72,
+  "ຶ": 73,
+  "ື": 74,
+  "ຸ": 75,
+  "ູ": 76,
+  "ົ": 77,
+  "ຼ": 78,
+  "ຽ": 79,
+  "ເ": 80,
+  "ແ": 81,
+  "ໂ": 82,
+  "ໃ": 83,
+  "ໄ": 84,
+  "ໆ": 85,
+  "່": 86,
+  "້": 87,
+  "໊": 88,
+  "໋": 89,
+  "ໍ": 90,
+  "ໜ": 91,
+  "ໝ": 92
+}