Push checkpoint-20000 with tokenizer files and diarization.py

.gitattributes

@@ -1,3 +1,4 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 tokenizer_config.json -filter -diff -merge text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- 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>" }}
+    {%- 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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- 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>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- 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') %}
+            {%- 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') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + 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 }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if true %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding": false,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "processor_class": "ASRProcessor",
+  "auto_map": {
+    "AutoProcessor": "asr_processing.ASRProcessor"
+  }
+}

projectors.py

@@ -85,7 +85,6 @@ class SimpleAdapter(nn.Module):
     def forward(self, x: torch.Tensor) -> torch.Tensor:
         return self.fc2(self.act(self.fc1(x)))
 
-
 class MOSAProjector(nn.Module):
     """MOSA-Base projector: simple 2-layer ReLU router with 4 simple adapters.
 
@@ -127,10 +126,7 @@ class MOSAProjector(nn.Module):
         # --- 3. Experts (Simple 2-layer GELU adapters) ---
         # Each expert: llm_dim -> hidden -> llm_dim (much smaller than frame-stacking)
         self.experts = nn.ModuleList(
-            [
-                SimpleAdapter(self.llm_dim, adapter_hidden, self.llm_dim)
-                for _ in range(self.num_experts)
-            ]
+            [SimpleAdapter(self.llm_dim, adapter_hidden, self.llm_dim) for _ in range(self.num_experts)]
         )
 
     def forward(self, x: torch.Tensor) -> torch.Tensor:
@@ -153,15 +149,18 @@ class MOSAProjector(nn.Module):
         routing_weights = F.softmax(self.router(x), dim=-1)  # (B, out_len, num_experts)
 
         # --- 3. Expert Mixture (Dense Execution) ---
-        expert_outputs = torch.stack([expert(x) for expert in self.experts])  # (E, B, out_len, D)
+        expert_outputs = torch.stack(
+            [expert(x) for expert in self.experts]
+        )  # (E, B, out_len, D)
         return torch.einsum("ebsd, bse -> bsd", expert_outputs, routing_weights)
 
     def get_output_length(self, input_length: int) -> int:
         """Calculate output sequence length after Conv1d downsampling (4x reduction)."""
         # Conv1d with stride 2, kernel 3, padding 1: out = (in + 2*1 - 3) // 2 + 1 = (in - 1) // 2 + 1
         # Applied twice for 4x total reduction
-        after_conv1 = (input_length + 2 * 1 - 3) // 2 + 1
-        return (after_conv1 + 2 * 1 - 3) // 2 + 1
+        length = (input_length + 2 * 1 - 3) // 2 + 1  # First conv
+        length = (length + 2 * 1 - 3) // 2 + 1  # Second conv
+        return length
 
 
 # =============================================================================

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b674fb8444e2553eae8f1b261093371920a28ef75b5c18f4deb3f9217ed0ba
+size 11422834