Upload folder using huggingface_hub

README.md

@@ -1,3 +1,34 @@
----
-license: cc-by-nc-4.0
----
+---
+license: cc-by-nc-4.0
+tags:
+- automatic-speech-recognition
+- wav2vec2
+- mms
+- speech
+---
+
+# MMS ASR – Custom Fine-tuned Model
+
+This model is a fine-tuned version of **Meta AI's Massively Multilingual Speech (MMS)** model
+for automatic speech recognition (ASR).
+
+## Base model
+- Meta AI – MMS (Wav2Vec2ForCTC)
+
+## License
+This model is released under the **Creative Commons Attribution–NonCommercial 4.0 (CC BY-NC 4.0)** license.
+
+You may use, modify, and share this model **for non-commercial purposes only**.
+Commercial use is **not permitted**.
+
+## Attribution
+Please cite:
+- Meta AI, *Massively Multilingual Speech (MMS)*
+
+## Usage
+```python
+from transformers import AutoProcessor, Wav2Vec2ForCTC
+
+processor = AutoProcessor.from_pretrained("sb-x/mms-1b-bbl")
+model = Wav2Vec2ForCTC.from_pretrained("sb-x/mms-1b-bbl")
+```

config.json

@@ -0,0 +1,108 @@
+{
+  "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": 0.05,
+  "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": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": 0,
+  "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": "4.57.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fdd3cf106f4f415cbc4eee1e79a96a9aa5f497887a19a0fd1dd75c870add48
+size 3858993404

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "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": "|"
+}

vocab.json

@@ -0,0 +1,53 @@
+{
+  "'": 5,
+  "-": 6,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "|": 4,
+  "́": 7,
+  "̂": 8,
+  "̆": 9,
+  "̦": 10,
+  "̧": 11,
+  "ა": 12,
+  "ბ": 13,
+  "გ": 14,
+  "დ": 15,
+  "ე": 16,
+  "ვ": 17,
+  "ზ": 18,
+  "თ": 19,
+  "ი": 20,
+  "კ": 21,
+  "ლ": 22,
+  "მ": 23,
+  "ნ": 24,
+  "ო": 25,
+  "პ": 26,
+  "ჟ": 27,
+  "რ": 28,
+  "ს": 29,
+  "ტ": 30,
+  "უ": 31,
+  "ფ": 32,
+  "ქ": 33,
+  "ღ": 34,
+  "ყ": 35,
+  "შ": 36,
+  "ჩ": 37,
+  "ც": 38,
+  "ძ": 39,
+  "წ": 40,
+  "ჭ": 41,
+  "ხ": 42,
+  "ჯ": 43,
+  "ჰ": 44,
+  "ჲ": 45,
+  "ჴ": 46,
+  "ჵ": 47,
+  "ჸ": 48,
+  "ჺ": 49,
+  "ჼ": 50
+}