Update tiny models for Qwen3ASRForConditionalGeneration

.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

chat_template.jinja

@@ -0,0 +1,8 @@
+{%- 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
+' + ns.system_text + '<|im_end|>
+' -}}{{- '<|im_start|>user
+' + ns2.audio_tokens + '<|im_end|>
+' -}}{%- for m in messages -%}{%- if m.role == 'assistant' -%}{%- set ns3 = namespace(assistant_text='') -%}{%- if m.content is string -%}{%- set ns3.assistant_text = m.content -%}{%- else -%}{%- for c in m.content -%}{%- if c.type == 'text' and (c.text is defined) -%}{%- set ns3.assistant_text = ns3.assistant_text + c.text -%}{%- endif -%}{%- endfor -%}{%- endif -%}{{- '<|im_start|>assistant
+' -}}{% generation %}{{- ns3.assistant_text + '<|im_end|>
+' -}}{% endgeneration %}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{- '<|im_start|>assistant
+' -}}{%- endif -%}

config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen3ASRForConditionalGeneration"
+  ],
+  "audio_config": {
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "attention_dropout": 0.0,
+    "d_model": 16,
+    "downsample_hidden_size": 4,
+    "dropout": 0.0,
+    "encoder_attention_heads": 2,
+    "encoder_ffn_dim": 16,
+    "encoder_layers": 1,
+    "initializer_range": 0.02,
+    "max_position_embeddings": 13,
+    "model_type": "qwen3_asr_encoder",
+    "n_window": 50,
+    "n_window_infer": 800,
+    "num_mel_bins": 20,
+    "output_dim": 16,
+    "scale_embedding": false
+  },
+  "audio_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "initializer_range": 0.02,
+  "model_type": "qwen3_asr",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 151645,
+    "head_dim": 8,
+    "hidden_act": "gelu",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_types": [
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 200,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151705
+  },
+  "tie_word_embeddings": true,
+  "timestamp_token_id": 151705,
+  "token_classification_bias": false,
+  "transformers_version": "5.16.0.dev0"
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 151645,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 151643,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b2a8e95330f8e8db910eb86f984e5b5212cd492b2875442208d273b23fab2a
+size 9747072

preprocessor_config.json

@@ -0,0 +1,16 @@
+{
+  "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
+}

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": true,
+  "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|>"
+}