Upload processor

chat_template.jinja

@@ -6,7 +6,8 @@
         {%- set keyword_namespace = namespace(items=[]) -%}
         {%- for item in content -%}
             {%- if item.type == 'audio' or 'audio' in item or 'audio_url' in item -%}
-                {{- '<|audio_start|><|audio_pad|><|audio_end|>\n' -}}
+                {{- '<|audio_start|><|audio_pad|><|audio_end|>
+' -}}
                 {%- set ns.has_audio = true -%}
             {%- elif item.type == 'text' and ns.text is none -%}
                 {%- set ns.text = item.text -%}
@@ -16,10 +17,14 @@
         {%- endfor -%}
         {%- if ns.has_audio -%}
             {%- if ns.text -%}
-                {{- '补充信息：' + ns.text + '\n\n' -}}
+                {{- '补充信息：' + ns.text + '
+
+' -}}
             {%- endif -%}
             {%- if keyword_namespace.items -%}
-                {{- '热词列表：[' + keyword_namespace.items|join(', ') + ']\n\n' -}}
+                {{- '热词列表：[' + keyword_namespace.items|join(', ') + ']
+
+' -}}
             {%- endif -%}
             {{- '请将音频转写为文本，每一段需以起始时间戳和说话人编号（[S01]、[S02]、[S03]…）开头，正文为对应的语音内容，并在段末标注结束时间戳，以清晰标明该段语音范围。' -}}
         {%- elif ns.text -%}
@@ -28,23 +33,45 @@
     {%- endif -%}
 {%- endmacro -%}
 {%- if tools %}
-    {{- '<|im_start|>system\n' }}
+    {{- '<|im_start|>system
+' }}
     {%- if messages[0].role == 'system' %}
-        {{- render_content(messages[0].content) + '\n\n' }}
+        {{- render_content(messages[0].content) + '
+
+' }}
     {%- else %}
-        {{- 'You are a helpful assistant.\n\n' }}
+        {{- 'You are a helpful assistant.
+
+' }}
     {%- endif %}
-    {{- "# 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>" }}
+    {{- "# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>" }}
     {%- for tool in tools %}
-        {{- "\n" }}
+        {{- "
+" }}
         {{- tool | tojson }}
     {%- endfor %}
-    {{- "\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" }}
+    {{- "
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call><|im_end|>
+" }}
 {%- else %}
     {%- if messages[0].role == 'system' %}
-        {{- '<|im_start|>system\n' + render_content(messages[0].content) + '<|im_end|>\n' }}
+        {{- '<|im_start|>system
+' + render_content(messages[0].content) + '<|im_end|>
+' }}
     {%- else %}
-        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+        {{- '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}
     {%- endif %}
 {%- endif %}
 {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
@@ -59,35 +86,51 @@
 {%- for message in messages %}
     {%- set content = render_content(message.content) %}
     {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
-        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>\n' }}
+        {{- '<|im_start|>' + message.role + '
+' + content + '<|im_end|>
+' }}
     {%- elif message.role == "assistant" %}
         {%- set reasoning_content = '' %}
         {%- if message.reasoning_content is string %}
             {%- set reasoning_content = message.reasoning_content %}
         {%- else %}
             {%- if '</think>' in content %}
-                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
-                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('
+').split('<think>')[-1].lstrip('
+') %}
+                {%- set content = content.split('</think>')[-1].lstrip('
+') %}
             {%- endif %}
         {%- endif %}
         {%- if loop.index0 > ns.last_query_index %}
             {%- if loop.last or (not loop.last and reasoning_content) %}
-                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+                {{- '<|im_start|>' + message.role + '
+<think>
+' + reasoning_content.strip('
+') + '
+</think>
+
+' + content.lstrip('
+') }}
             {%- else %}
-                {{- '<|im_start|>' + message.role + '\n' + content }}
+                {{- '<|im_start|>' + message.role + '
+' + content }}
             {%- endif %}
         {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
+            {{- '<|im_start|>' + message.role + '
+' + content }}
         {%- endif %}
         {%- if message.tool_calls %}
             {%- for tool_call in message.tool_calls %}
                 {%- if (loop.first and content) or (not loop.first) %}
-                    {{- '\n' }}
+                    {{- '
+' }}
                 {%- endif %}
                 {%- if tool_call.function %}
                     {%- set tool_call = tool_call.function %}
                 {%- endif %}
-                {{- '<tool_call>\n{"name": "' }}
+                {{- '<tool_call>
+{"name": "' }}
                 {{- tool_call.name }}
                 {{- '", "arguments": ' }}
                 {%- if tool_call.arguments is string %}
@@ -95,25 +138,36 @@
                 {%- else %}
                     {{- tool_call.arguments | tojson }}
                 {%- endif %}
-                {{- '}\n</tool_call>' }}
+                {{- '}
+</tool_call>' }}
             {%- endfor %}
         {%- endif %}
-        {{- '<|im_end|>\n' }}
+        {{- '<|im_end|>
+' }}
     {%- elif message.role == "tool" %}
         {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
             {{- '<|im_start|>user' }}
         {%- endif %}
-        {{- '\n<tool_response>\n' }}
+        {{- '
+<tool_response>
+' }}
         {{- content }}
-        {{- '\n</tool_response>' }}
+        {{- '
+</tool_response>' }}
         {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '<|im_end|>\n' }}
+            {{- '<|im_end|>
+' }}
         {%- endif %}
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
+    {{- '<|im_start|>assistant
+' }}
     {%- if enable_thinking is defined and enable_thinking is false %}
-        {{- '<think>\n\n</think>\n\n' }}
+        {{- '<think>
+
+</think>
+
+' }}
     {%- endif %}
-{%- endif %}
+{%- endif %}

processor_config.json

@@ -7,7 +7,7 @@
   "feature_extractor": {
     "chunk_length": 30,
     "dither": 0.0,
-    "feature_extractor_type": "WhisperFeatureExtractor",
+    "feature_extractor_type": "MossTranscribeDiarizeFeatureExtractor",
     "feature_size": 80,
     "hop_length": 160,
     "n_fft": 400,