End of training

README.md

@@ -0,0 +1,58 @@
+---
+base_model: charsiu/zh_w2v2_tiny_fc_10ms
+tags:
+- generated_from_trainer
+model-index:
+- name: wav2vec2_tiny_ja_roman
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wav2vec2_tiny_ja_roman
+
+This model is a fine-tuned version of [charsiu/zh_w2v2_tiny_fc_10ms](https://huggingface.co/charsiu/zh_w2v2_tiny_fc_10ms) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0716
+- eval_wer: 0.5521
+- eval_runtime: 26.495
+- eval_samples_per_second: 9.436
+- eval_steps_per_second: 1.208
+- epoch: 30.0
+- step: 4455
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 742
+- num_epochs: 50
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 27,
+  "<s>": 26
+}

config.json

@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.2,
+  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
@@ -44,27 +44,27 @@
   ],
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
-  "diversity_loss_weight": 100,
+  "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.2,
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.1,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.2,
+  "hidden_dropout": 0.1,
   "hidden_size": 384,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.2,
+  "layerdrop": 0.1,
   "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_prob": 0.1,
+  "mask_time_prob": 0.05,
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
   "num_attention_heads": 6,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9128c7826c4f156949ac47ad8e4e6ba0e7b93c26c690617fd6c2be1689ae9c2
+oid sha256:ddb4346afb7180e438637e043eba8ebe5ca5b97f1bfeb460f7512f20ef013de2
 size 93311728

preprocessor_config.json

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

runs/Jun28_21-48-52_975dce8c6ad7/events.out.tfevents.1719611397.975dce8c6ad7.25639.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ddf4a00a4fa28df5fb28415701b8617ef11a543470ba1bf5a82b2081a3f3ca4
-size 16823
+oid sha256:1bdc39f771a82d3191e80c897f6eaec267c338c52635c18554ed9919d5d74be0
+size 17456

runs/Jun29_01-29-58_975dce8c6ad7/events.out.tfevents.1719624667.975dce8c6ad7.66111.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399d5e2eb99d070c5bb3b09cd3d44039ccd32128d87ec3dea4c97c49f0e1d3d7
+size 4184

runs/Jun29_04-38-36_975dce8c6ad7/events.out.tfevents.1719635918.975dce8c6ad7.102313.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b490ce5b0ece29fedbccd307266796b3b60cbc6d97aa3e31155833b8d003389
+size 6227

runs/Jun29_09-50-30_975dce8c6ad7/events.out.tfevents.1719654635.975dce8c6ad7.102313.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7cb134363413a93d675f0fd160c3cab608d960cef943ab496de3f2f00fac1f
+size 6227

runs/Jun29_09-50-30_975dce8c6ad7/events.out.tfevents.1719654708.975dce8c6ad7.102313.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413b2d2b6cf64cc38eea338d0f8a98138bd5597e50c82012c908859ca48eed7d
+size 6227

runs/Jun29_09-50-30_975dce8c6ad7/events.out.tfevents.1719657697.975dce8c6ad7.102313.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05aac5e54830c8c1021cb9fc8e165c60c2979dd3eb61da4075cd7d383148b4a1
+size 6227

runs/Jun29_12-16-17_975dce8c6ad7/events.out.tfevents.1719663379.975dce8c6ad7.187009.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb17f7176192e38de6cc561263882d79fe6fd2ca0a70eb00c03a251ac7838540
+size 111511

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": {
+    "24": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "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 sha256:4b366df6da838987cc8209808de85e3910eceac771d699331347769c0e82e9c4
+oid sha256:1ed5514af681f78bf76be4a2729dd70222778da22f5a926a274f8aaf68461ab4
 size 5112

vocab.json

@@ -0,0 +1,28 @@
+{
+  "[PAD]": 25,
+  "[UNK]": 24,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "m": 12,
+  "n": 13,
+  "o": 14,
+  "p": 15,
+  "r": 16,
+  "s": 17,
+  "t": 18,
+  "u": 19,
+  "v": 20,
+  "w": 21,
+  "y": 22,
+  "z": 23,
+  "|": 0
+}