v1

.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

@@ -1,3 +1,95 @@
----
-license: gemma
----
+---
+license: gemma
+language:
+  - en
+base_model:
+  - google/gemma-3-270m-it
+library_name: transformers
+datasets:
+  - juno-labs/text-voice-activity-detection
+---
+
+This is a text-based Voice Activity Detection model that determines if a given speech fragment is complete enough for processing by a smart speaker assistant. This allows smart speakers to move from using time based pauses (300ms - 1000ms) to detect the end of voice input to using this model to determine if the voice input is complete.
+
+Example:
+
+- "Hey" -> no
+- "Hey Juno" -> no
+- "Hey Juno can you" -> no
+- "Hey Juno can you set" -> no
+- "Hey Juno can you set the" -> no
+- "Hey Juno can you set the temperature" -> no
+- "Hey Juno can you set the temperature to" -> no
+- "Hey Juno can you set the temperature to 65" -> yes
+
+Model prompting requirements:
+
+- Required system prompt: `"You are a Voice Activity Detection system. Determine if the given speech fragment is complete enough for processing. Answer with only 'yes' if complete or 'no' if incomplete."`
+- Required user prompt: `"Is this sentence fragment complete for processing: '{fragment}'"`
+
+To use with pipeline from transformers:
+
+```python
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="juno-labs/gemma-text-vad")
+
+SYSTEM_PROMPT = (
+  "You are a Voice Activity Detection system. "
+  "Determine if the given speech fragment is complete enough for processing. Answer with only 'yes' if complete or 'no' if incomplete."
+)
+
+SENTENCE = "Hey Juno can you set the temperature to"
+
+messages = [
+    {'content': SYSTEM_PROMPT, 'role': 'system'},
+    {'content': f"Is this sentence fragment complete for processing: '{SENTENCE}'", 'role': 'user'}
+]
+
+generated = pipe(messages)
+
+classification = generated[0]["generated_text"][2]["content"]
+
+print(f"Classification: {classification}") # "yes" or "no"
+```
+
+To use with transformers:
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL_ID = "juno-labs/gemma-text-vad"
+
+# Load model + tokenizer
+model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+SYSTEM_PROMPT = (
+    "You are a Voice Activity Detection system. "
+    "Determine if the given speech fragment is complete enough for processing. Answer with only 'yes' if complete or 'no' if incomplete."
+)
+
+SENTENCE = "Set the temperature to 68"
+
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {"role": "user", "content": f"Is this sentence fragment complete for processing: '{SENTENCE}'"},
+]
+
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=1,        # only 1 token
+        do_sample=False,         # greedy decoding
+        pad_token_id=tokenizer.eos_token_id,
+    )
+
+decoded = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
+
+print(f"Classification: {decoded}") # "yes" or "no"
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

config.json

@@ -0,0 +1,56 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "eos_token_id": 106,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.4",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.9.7",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "max_length": 32768,
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.55.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:282aa9a1b21353fa4595e1e1b958a223c199441c08f7068844e32afff0ea4047
+size 536223056

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074