Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,2 @@
-*.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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text

MODEL_INFO.json

@@ -0,0 +1,71 @@
+{
+  "model_name": "MMS Urmi ASR (fine-tuned adapters)",
+  "language": "urmi",
+  "task": "speech_recognition_ctc",
+  "best_checkpoint": {
+    "path_relative": "mms-urmi-out/checkpoint-8000",
+    "global_step": 8000,
+    "epoch_approx": 6.95,
+    "selection": "HuggingFace Trainer load_best_model_at_end; metric_key_for_best_model = eval_cer (lower is better)"
+  },
+  "eval_metrics_dev_split_at_best_step": {
+    "eval_cer": 0.23638727853930758,
+    "eval_wer": 0.7476359338061466,
+    "eval_loss": 0.7667429447174072
+  },
+  "eval_metrics_last_saved_checkpoints_for_reference": {
+    "checkpoint-16500": {
+      "eval_cer": 0.3157609579021509,
+      "eval_wer": 0.9042553191489362,
+      "eval_loss": 1.0155612230300903
+    },
+    "checkpoint-17000": {
+      "eval_cer": 0.3179281573386791,
+      "eval_wer": 0.9051418439716312,
+      "eval_loss": 1.0153851509094238
+    }
+  },
+  "base_pretrained_model": "facebook/mms-1b-all",
+  "fine_tuning_mode": "train_adapters_only (MMS attention adapters + lm_head; base wav2vec2 frozen)",
+  "config_highlights": {
+    "architecture": "Wav2Vec2ForCTC",
+    "hidden_size": 1280,
+    "num_hidden_layers": 48,
+    "vocab_size": 160,
+    "adapter_attn_dim": 16,
+    "transformers_version_used_in_training": "5.7.0"
+  },
+  "training_run": {
+    "script": "train_mms_urmi.py",
+    "train_dir": "5h_train",
+    "test_dir": "5h_test",
+    "output_dir": "./mms-urmi-out",
+    "wandb_project": "mms-urmi-asr",
+    "wandb_run_dir_example": "wandb/run-20260503_202229-6jkw5dsk",
+    "started_at_utc_note": "see wandb-metadata.json in that run folder",
+    "hardware_from_wandb": {
+      "gpu": "NVIDIA GeForce RTX 5090",
+      "cuda": "12.8",
+      "python": "3.12.13"
+    }
+  },
+  "archive_contents": [
+    "MODEL_INFO.json",
+    "model.safetensors",
+    "config.json",
+    "tokenizer_config.json",
+    "vocab.json",
+    "added_tokens.json",
+    "processor_config.json",
+    "trainer_state.json (from checkpoint-8000 only; partial training history)"
+  ],
+  "not_included_in_inference_archive": [
+    "optimizer.pt",
+    "scheduler.pt",
+    "scaler.pt",
+    "rng_state.pth",
+    "training_args.bin"
+  ],
+  "inference_dependencies": "see requirements_asr.txt in project root (torch, transformers, librosa, soundfile, etc.)",
+  "load_with_transformers_example": "from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor; import torch; model = Wav2Vec2ForCTC.from_pretrained('PATH_TO_EXTRACTED_FOLDER'); processor = Wav2Vec2Processor.from_pretrained('PATH_TO_EXTRACTED_FOLDER'); model.eval()"
+}

README.md

@@ -0,0 +1,70 @@
+---
+language: aii
+license: apache-2.0
+tags:
+  - automatic-speech-recognition
+  - wav2vec2
+  - ctc
+  - mms
+  - assyrian
+  - neo-aramaic
+  - aramaic
+  - syriac
+  - urmi
+  - urmia
+library_name: transformers
+pipeline_tag: automatic-speech-recognition
+base_model: facebook/mms-1b-all
+metrics:
+  - cer
+  - wer
+---
+
+# MMS Urmi ASR (adapter fine-tune, checkpoint step 8000)
+
+Speech recognition (CTC) for **Neo-Aramaic (Assyrian / Syriac tradition)**, **Urmi (Urmia) Christian dialect**. Hub metadata uses language code **`aii`** (Assyrian Neo-Aramaic, ISO 639-3), not the non-ISO label `urmi`. Fine-tuned from [`facebook/mms-1b-all`](https://huggingface.co/facebook/mms-1b-all). Training kept the wav2vec2 encoder frozen and updated **MMS attention adapters** and the **CTC head** only.
+
+## Metrics (dev split at best checkpoint)
+
+- **CER:** 0.236
+- **WER:** 0.748
+
+See `MODEL_INFO.json` in this repo for full training metadata.
+
+## Requirements
+
+- `transformers` ≥ 4.30 (config lists 5.7.0)
+- `torch`, `soundfile` or similar for audio I/O
+
+## Load and transcribe
+
+```python
+import torch
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import soundfile as sf
+
+model_id = "<YOUR_USERNAME>/<THIS_REPO_NAME>"  # after upload
+
+processor = Wav2Vec2Processor.from_pretrained(model_id)
+model = Wav2Vec2ForCTC.from_pretrained(model_id)
+model.eval()
+
+audio, sr = sf.read("audio.wav")
+if audio.ndim > 1:
+    audio = audio.mean(axis=1)
+if sr != 16000:
+    raise ValueError(f"Expected 16 kHz mono WAV; got sr={sr}")
+
+inputs = processor(audio, sampling_rate=16000, return_tensors="pt", padding=True)
+with torch.no_grad():
+    logits = model(inputs.input_values).logits
+pred_ids = torch.argmax(logits, dim=-1)
+text = processor.batch_decode(pred_ids)[0]
+print(text)
+```
+
+Local folder after clone/download works the same: pass the directory path instead of `model_id`.
+
+## Base model
+
+This checkpoint was trained from **facebook/mms-1b-all** with adapter-only updates; the saved `config.json` and weights in this repo are sufficient for `Wav2Vec2ForCTC.from_pretrained` without loading the base separately.

added_tokens.json

@@ -0,0 +1,8 @@
+{
+  " ": 154,
+  "ǧ": 155,
+  "ɣ": 156,
+  "̣": 157,
+  "ṗ": 158,
+  "ṭ": 159
+}

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": 0.0,
+  "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,
+  "dtype": "float32",
+  "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": 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": "5.7.0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 160,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb5be0a677460fa492b703e2805d4729379148e6f0d8fe69cc770b713b94dda
+size 3859551880

preprocessor_config.json

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

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>",
+  "word_delimiter_token": "|"
+}

tokenizer_config.json

@@ -0,0 +1,110 @@
+{
+  "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
+    },
+    "4": {
+      "content": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "154": {
+      "content": " ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "ǧ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "ɣ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "̣",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "ṗ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "ṭ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "backend": "custom",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "word_delimiter_token": "|"
+  },
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "eng",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}