Duplicated repository

README.md

@@ -0,0 +1,88 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: facebook/mms-1b-all
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: kbd-asr-colab2
+  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. -->
+
+# kbd-asr-colab2
+
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1829
+- Wer: 0.3182
+
+## 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: 0.001
+- 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: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.7968        | 0.1871 | 200  | 0.4521          | 0.7382 |
+| 0.6536        | 0.3742 | 400  | 0.3965          | 0.7499 |
+| 0.5989        | 0.5613 | 600  | 0.3850          | 0.7644 |
+| 0.5212        | 0.7484 | 800  | 0.3473          | 0.6373 |
+| 0.5649        | 0.9355 | 1000 | 0.2951          | 0.5633 |
+| 0.4996        | 1.1225 | 1200 | 0.2771          | 0.4806 |
+| 0.5247        | 1.3096 | 1400 | 0.2553          | 0.4592 |
+| 0.4559        | 1.4967 | 1600 | 0.2537          | 0.4396 |
+| 0.5153        | 1.6838 | 1800 | 0.2479          | 0.4364 |
+| 0.4622        | 1.8709 | 2000 | 0.2363          | 0.4251 |
+| 0.4533        | 2.0580 | 2200 | 0.2280          | 0.4091 |
+| 0.4529        | 2.2451 | 2400 | 0.2182          | 0.4066 |
+| 0.4453        | 2.4322 | 2600 | 0.2191          | 0.3902 |
+| 0.4339        | 2.6193 | 2800 | 0.2135          | 0.3815 |
+| 0.4179        | 2.8064 | 3000 | 0.2151          | 0.3906 |
+| 0.3983        | 2.9935 | 3200 | 0.2059          | 0.3725 |
+| 0.3868        | 3.1805 | 3400 | 0.2058          | 0.3614 |
+| 0.3804        | 3.3676 | 3600 | 0.1959          | 0.3558 |
+| 0.3934        | 3.5547 | 3800 | 0.2015          | 0.3555 |
+| 0.3693        | 3.7418 | 4000 | 0.1995          | 0.3587 |
+| 0.3678        | 3.9289 | 4200 | 0.2017          | 0.3876 |
+| 0.4097        | 4.1160 | 4400 | 0.1893          | 0.3355 |
+| 0.34          | 4.3031 | 4600 | 0.1877          | 0.3291 |
+| 0.3553        | 4.4902 | 4800 | 0.1857          | 0.3222 |
+| 0.3133        | 4.6773 | 5000 | 0.1839          | 0.3224 |
+| 0.3077        | 4.8644 | 5200 | 0.1829          | 0.3182 |
+
+
+### Framework versions
+
+- Transformers 4.50.0.dev0
+- Pytorch 2.5.1+cu121
+- Datasets 3.3.2
+- Tokenizers 0.21.0

adapter.kbd.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6904a9fc8edf02a6cf85f1511b73580044307e84cbc5453f777967e8e3922b7c
+size 8839532

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 38,
+  "<s>": 37
+}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/mms-1b-all",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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
+  ],
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 36,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 39,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f083d60000afa5c299a27313a26dd929fcb689974ffe00ecf6234e900c5e958
+size 3858931916

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

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": {
+    "35": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "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]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "kbd",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "*"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d77501bc4982904d3a78466efd119013e60105421b6db82cc6bc452a79e922
+size 5304

vocab.json

@@ -0,0 +1,41 @@
+{
+  "kbd": {
+    "*": 0,
+    "[PAD]": 36,
+    "[UNK]": 35,
+    "а": 1,
+    "б": 2,
+    "в": 3,
+    "г": 4,
+    "д": 5,
+    "е": 6,
+    "ж": 7,
+    "з": 8,
+    "и": 9,
+    "й": 10,
+    "к": 11,
+    "л": 12,
+    "м": 13,
+    "н": 14,
+    "о": 15,
+    "п": 16,
+    "р": 17,
+    "с": 18,
+    "т": 19,
+    "у": 20,
+    "ф": 21,
+    "х": 22,
+    "ц": 23,
+    "ч": 24,
+    "ш": 25,
+    "щ": 26,
+    "ъ": 27,
+    "ы": 28,
+    "ь": 29,
+    "э": 30,
+    "ю": 31,
+    "я": 32,
+    "ё": 33,
+    "ӏ": 34
+  }
+}