Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,39 @@
+---
+language: ar
+license: apache-2.0
+library_name: transformers
+pipeline_tag: automatic-speech-recognition
+base_model: Qwen/Qwen3-ASR-0.6B-hf
+datasets:
+- oddadmix/lahgtna-v3-small
+tags:
+- automatic-speech-recognition
+- arabic
+- dialectal-arabic
+- whisper
+metrics:
+- wer
+- cer
+---
+
+# qwen3-asr-0.6b-arabic-dialectal-v2
+
+**v2** — [`Qwen/Qwen3-ASR-0.6B-hf`](https://huggingface.co/Qwen/Qwen3-ASR-0.6B-hf) (0.6B) fine-tuned for
+multi-dialect Arabic on the **dialect-balanced** dataset
+[`oddadmix/lahgtna-v3-small`](https://huggingface.co/datasets/oddadmix/lahgtna-v3-small) (52k train / 2.6k test, **seed 42**,
+undiacritized output).
+
+> **Private / internal.** This is v2, trained on the *balanced, leakage-reduced*
+> data. v1 (trained on the earlier augmentation-expanded set, with the full
+> cross-model comparison + bundled fine-tuning scripts) is at
+> [`oddadmix/qwen3-asr-0.6b-arabic-dialectal`](https://huggingface.co/oddadmix/qwen3-asr-0.6b-arabic-dialectal).
+
+## Results (2,445-clip balanced test set, `clean_text` WER/CER)
+
+| | WER | CER |
+|---|---|---|
+| **This model (v2)** | **0.695** | 0.4244 |
+
+Full fine-tuning code, dependencies, and lessons are in the
+[v1 repo]( https://huggingface.co/oddadmix/qwen3-asr-0.6b-arabic-dialectal) (`train.py`, `normalize.py`,
+`FINETUNE.md`). This v2 uses the same recipe on the balanced dataset.

chat_template.jinja

@@ -0,0 +1,31 @@
+{%- set ns = namespace(system_text="") -%}
+{%- for m in messages -%}
+  {%- if m.role == 'system' -%}
+    {%- if m.content is string -%}
+      {%- set ns.system_text = ns.system_text + m.content -%}
+    {%- else -%}
+      {%- for c in m.content -%}
+        {%- if c.type == 'text' and (c.text is defined) -%}
+          {%- set ns.system_text = ns.system_text + c.text -%}
+        {%- endif -%}
+      {%- endfor -%}
+    {%- endif -%}
+  {%- endif -%}
+{%- endfor -%}
+
+{%- set ns2 = namespace(audio_tokens="") -%}
+{%- for m in messages -%}
+  {%- if m.content is not string -%}
+    {%- for c in m.content -%}
+      {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}
+        {%- set ns2.audio_tokens = ns2.audio_tokens + "<|audio_start|><|audio_pad|><|audio_end|>" -%}
+      {%- endif -%}
+    {%- endfor -%}
+  {%- endif -%}
+{%- endfor -%}
+
+{{- '<|im_start|>system\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\n' -}}
+{{- '<|im_start|>user\n' + ns2.audio_tokens + '<|im_end|>\n' -}}
+{%- if add_generation_prompt -%}
+{{- '<|im_start|>assistant\n' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,100 @@
+{
+  "architectures": [
+    "Qwen3ASRForConditionalGeneration"
+  ],
+  "audio_config": {
+    "activation_dropout": 0,
+    "activation_function": "gelu",
+    "attention_dropout": 0,
+    "conv_chunksize": 500,
+    "d_model": 896,
+    "downsample_hidden_size": 480,
+    "dropout": 0,
+    "dtype": "bfloat16",
+    "encoder_attention_heads": 14,
+    "encoder_ffn_dim": 3584,
+    "encoder_layers": 18,
+    "initializer_range": 0.02,
+    "max_position_embeddings": 13,
+    "model_type": "qwen3_asr_encoder",
+    "n_window": 50,
+    "n_window_infer": 800,
+    "num_key_value_heads": 14,
+    "num_mel_bins": 128,
+    "output_dim": 1024,
+    "scale_embedding": false
+  },
+  "audio_token_id": 151676,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    151643,
+    151645
+  ],
+  "initializer_range": 0.02,
+  "model_type": "qwen3_asr",
+  "pad_token_id": 151645,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": null,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 65536,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "timestamp_token_id": 151705,
+  "token_classification_bias": false,
+  "transformers_version": "5.14.0.dev0",
+  "use_cache": false
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "do_sample": false,
+  "eos_token_id": [
+    151643,
+    151645
+  ],
+  "max_new_tokens": 512,
+  "pad_token_id": 151645,
+  "transformers_version": "5.14.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3dabb550e4681fee7a578ac41942e00bd8a793afe426e747ef299e334008ac
+size 1564928088

processor_config.json

@@ -0,0 +1,20 @@
+{
+  "feature_extractor": {
+    "chunk_length": 30,
+    "dither": 0.0,
+    "feature_extractor_type": "Qwen3ASRFeatureExtractor",
+    "feature_size": 128,
+    "hop_length": 160,
+    "min_length": 8000,
+    "n_fft": 400,
+    "n_samples": 480000,
+    "n_window": 50,
+    "nb_max_frames": 3000,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "processor_class": "Qwen3ASRProcessor",
+  "timestamp_segment_time": 80
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1fad59be22a41ee293363fcf95fdedbc7c93f3b49270b1d2e18bd1399a7a05
+size 11429653

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3ASRProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}