Upload omniASR-W2V-1B converted from fairseq2

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+tags:
+- speech
+- audio
+- wav2vec2
+- feature-extraction
+pipeline_tag: feature-extraction
+---
+
+# omniASR-W2V-1B
+
+Wav2Vec2 SSL encoder (1B) converted from the [OmniLingual](https://github.com/facebookresearch/omnilingual-asr) fairseq2 checkpoint `omniASR_W2V_1B`.
+
+This is the **pre-trained encoder backbone without a CTC head**, suitable for feature extraction, probing, and fine-tuning on downstream speech tasks.
+
+## Model details
+
+| Property             | Value |
+|---|---|
+| HF class             | `Wav2Vec2Model` |
+| Encoder layers       | 48 |
+| Hidden size          | 1280 |
+| Attention heads      | 20 |
+| FFN intermediate     | 5120 |
+| Source framework     | fairseq2 |
+| Source card          | `omniASR_W2V_1B` |
+| Parity verification  | ⚠️ Verification failed |
+
+
+A parity check was run but reported a mismatch. Use with caution and open an issue if you observe unexpected behaviour.
+
+## Usage
+
+```python
+from transformers import Wav2Vec2Model, Wav2Vec2FeatureExtractor
+import torch, torchaudio
+
+extractor = Wav2Vec2FeatureExtractor.from_pretrained("aadel4/omniASR-W2V-1B")
+model     = Wav2Vec2Model.from_pretrained("aadel4/omniASR-W2V-1B")
+model.eval()
+
+waveform, sr = torchaudio.load("audio.wav")
+if sr != 16_000:
+    waveform = torchaudio.functional.resample(waveform, sr, 16_000)
+
+inputs = extractor(
+    waveform.squeeze().numpy(), sampling_rate=16_000,
+    return_tensors="pt", padding=True
+)
+with torch.no_grad():
+    embeddings = model(**inputs).last_hidden_state  # (1, T, 1280)
+```

config.json

@@ -0,0 +1,106 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2Model"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "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": "sum",
+  "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_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "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": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 20,
+  "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": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "5.3.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89821b842a34e75e69556fb7e42ac2ad6da9d9f2e7a824625ad01203bccd39b8
+size 3850083584

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "sampling_rate": 16000,
+  "padding_value": 0.0,
+  "do_normalize": true,
+  "return_attention_mask": false
+}