Upload VibeVoice Arabic LoRA adapters (improved)

README.md

@@ -0,0 +1,11 @@
+
+---
+license: apache-2.0
+base_model: aoi-ot/VibeVoice-Large
+language:
+- ar
+---
+
+# VibeVoice Arabic LoRA v2
+
+This is a LoRA adapter for the `aoi-ot/VibeVoice-Large` model, fine-tuned on an Arabic speech dataset.

acoustic_connector/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f2bb0ab08d4a2fa78688dcaa119cac855a69b7a83e572af14cef989528c828
+size 26173211

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050cb3366d0ca6a11ed7208350035eb07683acfbbfc9a9f3295dc05ec46cbf24
+size 80789744

diffusion_head/config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "VibeVoiceDiffusionHead"
+  ],
+  "ddpm_batch_mul": 4,
+  "ddpm_beta_schedule": "cosine",
+  "ddpm_num_inference_steps": 20,
+  "ddpm_num_steps": 1000,
+  "diffusion_type": "ddpm",
+  "head_ffn_ratio": 3.0,
+  "head_layers": 4,
+  "hidden_size": 3584,
+  "latent_size": 64,
+  "model_type": "vibevoice_diffusion_head",
+  "prediction_type": "v_prediction",
+  "rms_norm_eps": 1e-05,
+  "speech_vae_dim": 64,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3"
+}

diffusion_head/diffusion_head_full.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14dda464996c9b3355454f65eba95d8d50404a49a437398eed314d7f09378675
+size 1338678485

diffusion_head/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3f859b166ddec6cfce5a877a49f119fb36b5b318272f00dae452082b4a0f96
+size 1338669752

diffusion_head_full.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14dda464996c9b3355454f65eba95d8d50404a49a437398eed314d7f09378675
+size 1338678485

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "processor_class": "VibeVoiceProcessor",
+  "speech_tok_compress_ratio": 3200,
+  "db_normalize": true,
+  "audio_processor": {
+    "feature_extractor_type": "VibeVoiceTokenizerProcessor",
+    "sampling_rate": 24000,
+    "normalize_audio": true,
+    "target_dB_FS": -25,
+    "eps": 1e-06
+  },
+  "language_model_pretrained_name": "Qwen/Qwen2.5-7B"
+}

semantic_connector/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b642f2a128d0d4d73faec28787b730f5a9957169f37a0bcfbdda4454acf170
+size 26631963