初始化项目，由ModelHub XC社区提供模型

Model: hassanaitnacer/wav2vec2-large-xlsr-moroccan-darija-v4 Source: Original Platform
2026-05-15 20:09:06 +08:00
commit 2800de32db
11 changed files with 418 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: hassanaitnacer/wav2vec2-large-xlsr-moroccan-darija-v3
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wav2vec2-large-xlsr-moroccan-darija-v4
+  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-large-xlsr-moroccan-darija-v4
+
+This model is a fine-tuned version of [hassanaitnacer/wav2vec2-large-xlsr-moroccan-darija-v3](https://huggingface.co/hassanaitnacer/wav2vec2-large-xlsr-moroccan-darija-v3) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0394
+- Wer: 0.0816
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.0512        | 1.0225 | 500  | 0.0410          | 0.0872 |
+| 0.0629        | 2.0450 | 1000 | 0.0508          | 0.0844 |
+| 0.0384        | 3.0675 | 1500 | 0.0394          | 0.0816 |
+
+
+### Framework versions
+
+- Transformers 4.43.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,8 @@
+{
+  "</s>": 66,
+  "<s>": 65,
+  "پ": 70,
+  "چ": 68,
+  "ڤ": 67,
+  "گ": 69
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "hassanaitnacer/wav2vec2-large-xlsr-moroccan-darija-v3",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "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": 768,
+  "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": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 64,
+  "proj_codevector_dim": 768,
+  "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": "4.43.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 71,
+  "xvector_output_dim": 512
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4549d68408e72256503148794dd4fe8056e4bfcd701b69d970b72a35b2358372
+size 1262098580
--- a/preprocessor_config.json
+++ b/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
+}
--- a/runs/Jul04_11-33-22_31c1ed75f77e/events.out.tfevents.1720093200.31c1ed75f77e.719.0
+++ b/runs/Jul04_11-33-22_31c1ed75f77e/events.out.tfevents.1720093200.31c1ed75f77e.719.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337c7584b1387fbe73ec94d4d2aacc0f35091dbd88c7a91355daa48fe7ea53b6
+size 8638
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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
+  }
+}
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,79 @@
+{
+  "added_tokens_decoder": {
+    "63": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "ڤ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "چ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "گ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "پ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feaa51f2f7cbdb3b341761d711e13f05045c7d424d06f97f5e30b94177147945
+size 5240
--- a/vocab.json
+++ b/vocab.json
@@ -0,0 +1,67 @@
+{
+  "\n": 58,
+  "@": 5,
+  "[PAD]": 64,
+  "[UNK]": 63,
+  "_": 1,
+  "a": 53,
+  "c": 45,
+  "d": 16,
+  "e": 47,
+  "h": 49,
+  "i": 23,
+  "k": 27,
+  "n": 14,
+  "o": 51,
+  "p": 55,
+  "r": 24,
+  "s": 31,
+  "t": 32,
+  "v": 25,
+  "|": 2,
+  "؟": 48,
+  "ء": 29,
+  "آ": 10,
+  "أ": 56,
+  "ؤ": 36,
+  "إ": 62,
+  "ئ": 17,
+  "ا": 0,
+  "ب": 50,
+  "ة": 18,
+  "ت": 43,
+  "ث": 13,
+  "ج": 15,
+  "ح": 60,
+  "خ": 59,
+  "د": 54,
+  "ذ": 6,
+  "ر": 30,
+  "ز": 20,
+  "س": 52,
+  "ش": 8,
+  "ص": 11,
+  "ض": 38,
+  "ط": 42,
+  "ظ": 46,
+  "ع": 21,
+  "غ": 9,
+  "ـ": 34,
+  "ف": 22,
+  "ق": 37,
+  "ك": 3,
+  "ل": 40,
+  "م": 39,
+  "ن": 4,
+  "ه": 19,
+  "و": 61,
+  "ى": 33,
+  "ي": 12,
+  "ِ": 28,
+  "ّ": 44,
+  "ْ": 57,
+  "ٖ": 7,
+  "ڸ": 26,
+  " ": 35,
+  "…": 41
+}