Upload XLS-R Lao ASR model

README.md

@@ -1,3 +1,47 @@
----
-license: apache-2.0
----
+---
+language: lo
+license: apache-2.0
+tags:
+- automatic-speech-recognition
+- speech
+- audio
+- lao
+- wav2vec2
+- xls-r
+datasets:
+- h3llohihi/lao-asr-thesis-dataset
+---
+
+# XLS-R Lao ASR
+
+Fine-tuned XLS-R-300M model for Lao automatic speech recognition.
+
+## Model Performance
+- **Test CER**: 15.14%
+- **Training Time**: 2.1 hours
+- **Dialects**: Central, Northern, Southern Lao
+
+## Usage
+
+```python
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import torch
+import librosa
+
+# Load model and processor
+model = Wav2Vec2ForCTC.from_pretrained("h3llohihi/xls-r-lao-asr")
+processor = Wav2Vec2Processor.from_pretrained("h3llohihi/xls-r-lao-asr")
+
+# Load audio
+audio, sr = librosa.load("audio.wav", sr=16000)
+
+# Process audio
+inputs = processor(audio, sampling_rate=16000, return_tensors="pt")
+
+# Generate prediction
+with torch.no_grad():
+    logits = model(**inputs).logits
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = processor.batch_decode(predicted_ids)[0]
+
+print(transcription)

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 56,
+  "<s>": 55
+}

config.json

@@ -0,0 +1,108 @@
+{
+  "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": 0.1,
+  "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": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 0.075,
+  "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": 0,
+  "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": "4.52.4",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 57,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0282c350405915a500648ae0dca13cc5523cac618c5b80984eec0840259a017a
+size 1262041180

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
+}

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 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "56": {
+      "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": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,57 @@
+{
+  " ": 2,
+  "<pad>": 0,
+  "<unk>": 1,
+  "ກ": 3,
+  "ຂ": 4,
+  "ຄ": 5,
+  "ງ": 6,
+  "ຈ": 7,
+  "ຊ": 8,
+  "ຍ": 9,
+  "ດ": 10,
+  "ຕ": 11,
+  "ຖ": 12,
+  "ທ": 13,
+  "ນ": 14,
+  "ບ": 15,
+  "ປ": 16,
+  "ຜ": 17,
+  "ຝ": 18,
+  "ພ": 19,
+  "ຟ": 20,
+  "ມ": 21,
+  "ຢ": 22,
+  "ຣ": 23,
+  "ລ": 24,
+  "ວ": 25,
+  "ສ": 26,
+  "ຫ": 27,
+  "ອ": 28,
+  "ຮ": 29,
+  "ະ": 30,
+  "ັ": 31,
+  "າ": 32,
+  "ຳ": 33,
+  "ິ": 34,
+  "ີ": 35,
+  "ຶ": 36,
+  "ື": 37,
+  "ຸ": 38,
+  "ູ": 39,
+  "ົ": 40,
+  "ຼ": 41,
+  "ຽ": 42,
+  "ເ": 43,
+  "ແ": 44,
+  "ໂ": 45,
+  "ໃ": 46,
+  "ໄ": 47,
+  "ໆ": 48,
+  "່": 49,
+  "້": 50,
+  "໋": 51,
+  "ໍ": 52,
+  "ໜ": 53,
+  "ໝ": 54
+}