End of training

README.md

@@ -0,0 +1,51 @@
+---
+library_name: transformers
+license: mit
+base_model: facebook/w2v-bert-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the None dataset.
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2500
+- training_steps: 25000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.53.2
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.2

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 42,
-  "<s>": 41
+  "</s>": 67,
+  "<s>": 66
 }

config.json

@@ -1,85 +1,56 @@
 {
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
   "activation_dropout": 0.0,
-  "adapter_attn_dim": null,
+  "adapter_act": "relu",
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
+  "add_adapter": true,
+  "apply_spec_augment": false,
   "architectures": [
-    "Wav2Vec2ForCTC"
+    "Wav2Vec2BertForCTC"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
-  "classifier_proj_size": 256,
+  "classifier_proj_size": 768,
   "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
-  "conv_dim": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "conv_kernel": [
-    10,
-    3,
-    3,
-    3,
-    3,
-    2,
-    2
-  ],
-  "conv_stride": [
-    5,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2
-  ],
+  "conv_depthwise_kernel_size": 31,
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
   "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
   "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
   "hidden_dropout": 0.1,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
   "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": 0.05,
-  "model_type": "wav2vec2",
-  "num_adapter_layers": 3,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
   "num_attention_heads": 16,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 40,
+  "pad_token_id": 65,
+  "position_embeddings_type": "relative_key",
   "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
   "tdnn_dilation": [
     1,
     2,
@@ -102,8 +73,9 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.53.2",
+  "use_intermediate_ffn_before_adapter": false,
   "use_weighted_layer_sum": false,
-  "vocab_size": 43,
+  "vocab_size": 68,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd7bb5fa971ca516e73a5d89bd019bf74400d9a69bf980a8569235df774ff86
-size 1261983780
+oid sha256:f2031f2b1d22ccd285550da43b09e166eb1c682bcb1ab58a150d8289dda7c82e
+size 2423097560

preprocessor_config.json

@@ -1,10 +1,11 @@
 {
-  "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
-  "feature_size": 1,
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
   "padding_side": "right",
-  "padding_value": 0.0,
-  "processor_class": "Wav2Vec2Processor",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
   "return_attention_mask": true,
-  "sampling_rate": 16000
+  "sampling_rate": 16000,
+  "stride": 2
 }

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "39": {
+    "64": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "40": {
+    "65": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "41": {
+    "66": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "42": {
+    "67": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,7 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2Processor",
+  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a382a06010474ba7fcd3018791c974260b093b1619e654ea910979fa2f729840
+oid sha256:483152d7aa715022a9aa872223d78a024157391bde94813dcaf228b4a12b762d
 size 5368

vocab.json

@@ -1,43 +1,68 @@
 {
   "0": 1,
   "1": 2,
-  "2": 3,
-  "3": 4,
-  "4": 5,
-  "5": 6,
-  "6": 7,
-  "7": 8,
-  "8": 9,
-  "9": 10,
-  "[PAD]": 40,
-  "[UNK]": 39,
-  "a": 11,
-  "b": 12,
-  "c": 13,
-  "d": 14,
-  "e": 15,
-  "f": 16,
-  "g": 17,
-  "h": 18,
-  "i": 19,
-  "j": 20,
-  "k": 21,
-  "l": 22,
-  "m": 23,
-  "n": 24,
-  "o": 25,
-  "p": 26,
-  "q": 27,
-  "r": 28,
-  "s": 29,
-  "t": 30,
-  "u": 31,
-  "v": 32,
-  "w": 33,
-  "x": 34,
-  "y": 35,
-  "z": 36,
+  "9": 3,
+  "[PAD]": 65,
+  "[UNK]": 64,
+  "a": 4,
+  "b": 5,
+  "c": 6,
+  "d": 7,
+  "e": 8,
+  "f": 9,
+  "g": 10,
+  "h": 11,
+  "i": 12,
+  "j": 13,
+  "k": 14,
+  "l": 15,
+  "m": 16,
+  "n": 17,
+  "o": 18,
+  "p": 19,
+  "q": 20,
+  "r": 21,
+  "s": 22,
+  "t": 23,
+  "u": 24,
+  "v": 25,
+  "w": 26,
+  "x": 27,
+  "y": 28,
+  "z": 29,
   "|": 0,
-  "é": 37,
-  "ì": 38
+  "~": 30,
+  "à": 31,
+  "á": 32,
+  "ã": 33,
+  "è": 34,
+  "é": 35,
+  "ì": 36,
+  "í": 37,
+  "ò": 38,
+  "ó": 39,
+  "õ": 40,
+  "ù": 41,
+  "ú": 42,
+  "ā": 43,
+  "ē": 44,
+  "ĩ": 45,
+  "ŋ": 46,
+  "ũ": 47,
+  "ū": 48,
+  "ƒ": 49,
+  "ɔ": 50,
+  "ɖ": 51,
+  "ɛ": 52,
+  "ɣ": 53,
+  "ʋ": 54,
+  "̀": 55,
+  "́": 56,
+  "̃": 57,
+  "̄": 58,
+  "ͻ": 59,
+  "ε": 60,
+  "ѐ": 61,
+  "ẽ": 62,
+  "ὸ": 63
 }