Update split-layout Transformers checkpoint

Publish the checkpoint and processor artifacts validated for huggingface/transformers#46180. The model loads with zero missing, unexpected, or mismatched keys and passes the H100 English transcription quickstart. Also replace the stale preprocessor config and add model-card usage instructions.

README.md

@@ -34,11 +34,40 @@ This model is part of the **FunASR** ecosystem — one industrial-grade open-sou
 
 </div>
 
+# Fun-ASR-Nano (Hugging Face Transformers)
 
-# Fun-ASR-Nano (HuggingFace Transformers)
-
-This is the HuggingFace Transformers-compatible version of [Fun-ASR-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512).
+This is the Hugging Face Transformers-compatible version of [Fun-ASR-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512).
 
 Fun-ASR-Nano is an end-to-end speech recognition model by [FunAudioLLM](https://github.com/FunAudioLLM), trained on tens of millions of hours of real speech data. It supports multilingual speech recognition covering Chinese (with dialects), English, Japanese, Korean, and many more languages.
 
-For full documentation, benchmarks, and usage instructions, please refer to the [main model card](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512).
+## Transformers quickstart
+
+Fun-ASR-Nano support is being added to Transformers in [huggingface/transformers#46180](https://github.com/huggingface/transformers/pull/46180). Until it is included in a Transformers release, use a build containing that PR.
+
+```python
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
+
+model_id = "FunAudioLLM/Fun-ASR-Nano-2512-hf"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    model_id,
+    dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+audio_url = "https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512/resolve/main/example/en.mp3"
+inputs = processor.apply_transcription_request(audio=audio_url, return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(**inputs, max_new_tokens=200)
+generated_ids = generated_ids[:, inputs.input_ids.shape[1] :]
+print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0])
+```
+
+Expected transcription:
+
+```text
+The tribal chieftain called for the boy, and presented him with fifty pieces of gold.
+```
+
+For batch inference, training, `torch.compile`, benchmarks, and the full model description, see the [Transformers documentation](https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/fun_asr_nano.md) and the [original model card](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512).

config.json

@@ -1,23 +1,23 @@
 {
-  "adaptor_attention_heads": 8,
   "adaptor_downsample_rate": 1,
-  "adaptor_dropout_rate": 0.0,
-  "adaptor_ffn_dim": 2048,
-  "adaptor_num_layers": 2,
+  "adaptor_dropout": 0.0,
+  "adaptor_intermediate_size": 2048,
+  "adaptor_num_attention_heads": 8,
+  "adaptor_num_hidden_layers": 2,
   "architectures": [
     "FunAsrNanoForConditionalGeneration"
   ],
   "audio_encoder_config": {
-    "attention_dropout_rate": 0.1,
-    "attention_heads": 4,
-    "dropout_rate": 0.1,
+    "attention_dropout": 0.0,
+    "dropout": 0.1,
+    "encoder_layers": 50,
     "initializer_range": 0.02,
     "input_size": 560,
+    "intermediate_size": 2048,
     "kernel_size": 11,
-    "linear_units": 2048,
     "model_type": "fun_asr_nano_encoder",
-    "num_blocks": 50,
-    "output_size": 512,
+    "num_attention_heads": 4,
+    "output_dim": 512,
     "sanm_shift": 0,
     "tp_blocks": 20
   },
@@ -87,5 +87,6 @@
     "use_sliding_window": false,
     "vocab_size": 151936
   },
+  "tie_word_embeddings": true,
   "transformers_version": "5.13.0.dev0"
 }

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ff80cd0dc665baf82adac89f68b788e56c75815351c46227366ae3791bdd7f
-size 1970908640
+oid sha256:bc11982f1cb33c77c21208365d3a1a19cf103cf4a0b1cab96684b70728b231ab
+size 1659742664

preprocessor_config.json

@@ -1,12 +0,0 @@
-{
-  "feature_extractor_type": "FunAsrNanoFeatureExtractor",
-  "feature_size": 80,
-  "sampling_rate": 16000,
-  "frame_length": 25,
-  "frame_shift": 10,
-  "lfr_m": 7,
-  "lfr_n": 6,
-  "window": "hamming",
-  "padding_value": 0.0,
-  "return_attention_mask": true
-}

processor_config.json

@@ -1,6 +1,20 @@
 {
-  "processor_class": "FunAsrNanoProcessor",
-  "auto_map": {
-    "AutoProcessor": "processing_fun_asr_nano.FunAsrNanoProcessor"
-  }
-}
+  "audio_downsample_rate": 1,
+  "audio_token": "<|object_ref_start|>",
+  "default_transcription_prompt": "Transcribe the audio:",
+  "feature_extractor": {
+    "feature_extractor_type": "FunAsrNanoFeatureExtractor",
+    "feature_size": 80,
+    "frame_length": 25,
+    "frame_shift": 10,
+    "lfr_m": 7,
+    "lfr_n": 6,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "preemphasis": 0.97,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "max_audio_len": null,
+  "processor_class": "FunAsrNanoProcessor"
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -1,217 +1,11 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>",
     "<|object_ref_start|>",
@@ -226,13 +20,11 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
+  "processor_class": "FunAsrNanoProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null