Model save

Browse files

Files changed (9) hide show

README.md +69 -0
added_tokens.json +4 -0
config.json +107 -0
model.safetensors +3 -0
preprocessor_config.json +10 -0
special_tokens_map.json +6 -0
tokenizer_config.json +49 -0
training_args.bin +3 -0
vocab.json +67 -0

README.md ADDED Viewed

	@@ -0,0 +1,69 @@

+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: facebook/mms-1b-all
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: mms-multilingual-sa
+  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. -->
+# mms-multilingual-sa
+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: 0.4480
+- Wer: 0.4560
+- Cer: 0.1169
+## 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: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
+- training_steps: 2000
+### Training results
+| Training Loss | Epoch  | Step | Validation Loss | Wer    | Cer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
+| 0.4834        | 6.008  | 400  | 0.5114          | 0.5473 | 0.1398 |
+| 0.3568        | 12.016 | 800  | 0.4518          | 0.4777 | 0.1217 |
+| 0.3151        | 18.024 | 1200 | 0.4488          | 0.4686 | 0.1199 |
+| 0.2918        | 24.032 | 1600 | 0.4503          | 0.4557 | 0.1168 |
+| 0.2715        | 31.008 | 2000 | 0.4480          | 0.4560 | 0.1169 |
+### Framework versions
+- Transformers 4.57.3
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "</s>": 64,
+  "<s>": 63
+}

config.json ADDED Viewed

	@@ -0,0 +1,107 @@

+{
+  "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": 63,
+  "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": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "dtype": "float32",
+  "eos_token_id": 64,
+  "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": 62,
+  "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
+  ],
+  "transformers_version": "4.57.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 65,
+  "xvector_output_dim": 512
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6361352800bc66ee12ff755839a7c5ad331b693f5f19745b7d698b74e982cbae
+size 3859065140

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,49 @@

+{
+  "added_tokens_decoder": {
+    "61": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64": {
+      "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": "zul",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:56f58810a80c9fca74db6645e3b36fae0b3c892acc3f7dce75c5134f1769b4bd
+size 5969

vocab.json ADDED Viewed

	@@ -0,0 +1,67 @@

+{
+  "zul": {
+    "0": 1,
+    "1": 2,
+    "2": 3,
+    "3": 4,
+    "4": 5,
+    "5": 6,
+    "6": 7,
+    "7": 8,
+    "8": 9,
+    "9": 10,
+    "[PAD]": 62,
+    "[UNK]": 61,
+    "_": 11,
+    "a": 12,
+    "b": 13,
+    "c": 14,
+    "d": 15,
+    "e": 16,
+    "f": 17,
+    "g": 18,
+    "h": 19,
+    "i": 20,
+    "j": 21,
+    "k": 22,
+    "l": 23,
+    "m": 24,
+    "n": 25,
+    "o": 26,
+    "p": 27,
+    "q": 28,
+    "r": 29,
+    "s": 30,
+    "t": 31,
+    "u": 32,
+    "v": 33,
+    "w": 34,
+    "x": 35,
+    "y": 36,
+    "z": 37,
+    "|": 0,
+    "à": 38,
+    "ã": 39,
+    "å": 40,
+    "ç": 41,
+    "é": 42,
+    "ê": 43,
+    "ë": 44,
+    "í": 45,
+    "î": 46,
+    "ó": 47,
+    "ô": 48,
+    "ø": 49,
+    "ü": 50,
+    "ā": 51,
+    "ī": 52,
+    "š": 53,
+    "ȇ": 54,
+    "ȏ": 55,
+    "ḓ": 56,
+    "ḽ": 57,
+    "ṅ": 58,
+    "ṋ": 59,
+    "ṱ": 60
+  }
+}