Upload GPT-TTS-int8-light

.gitattributes

@@ -36,3 +36,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 figures/GPA.png filter=lfs diff=lfs merge=lfs -text
 figures/GPA_intro.png filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+
+*.onnx.data filter=lfs diff=lfs merge=lfs -text

GPA_TTS/GPA_TTS_INT8/model/qwen_int4_ort/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

GPA_TTS/GPA_TTS_INT8/model/qwen_int4_ort/genai_config.json

@@ -0,0 +1,51 @@
+{
+    "model": {
+        "bos_token_id": 1,
+        "context_length": 32768,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": []
+            },
+            "filename": "model.onnx",
+            "head_size": 128,
+            "hidden_size": 512,
+            "inputs": {
+                "input_ids": "input_ids",
+                "attention_mask": "attention_mask",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 16,
+            "num_hidden_layers": 28,
+            "num_key_value_heads": 8
+        },
+        "eos_token_id": [
+            151645
+        ],
+        "pad_token_id": 151643,
+        "type": "qwen3",
+        "vocab_size": 180445
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 32768,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": true,
+        "repetition_penalty": 1.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0
+    }
+}

GPA_TTS/GPA_TTS_INT8/model/qwen_int4_ort/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3ce04936a4722cc907faa16ee9f1391bd88f5a345f1394933ac3ffe3f837ff
+size 327027

GPA_TTS/GPA_TTS_INT8/model/qwen_int4_ort/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00ce27dd0d8aff161c3b9f98399bc2817a6478fae29f05397d4e58d25e6473e
+size 212393216

GPA_TTS/GPA_TTS_INT8/model/qwen_int4_ort/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

GPA_TTS/GPA_TTS_INT8/model/qwen_int4_ort/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01db113d2ddc9192eaed1145c5caced436dbac3e60ee7238b662caf426ecc9f3
+size 17114145

GPA_TTS/GPA_TTS_INT8/model/reference/038142_global_tokens.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af085e80826c70ba3580c9355ad65084dbd6234c1f9dece87c114e1d3cfe269c
+size 384

GPA_TTS/GPA_TTS_INT8/model/runtime_manifest.json

@@ -0,0 +1,11 @@
+{
+  "sample_rate": 16000,
+  "latent_hop_length": 320,
+  "global_token_offset": 168111,
+  "global_tokens_shape": [
+    1,
+    1,
+    32
+  ],
+  "eos_token": "<|im_end|>"
+}

GPA_TTS/GPA_TTS_INT8/model/spark_detokenizer_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2715eb8f0906f7cabbe73eb74c61c532897bf1d64221c79a79e7e82fafa6fb8
+size 1896712

GPA_TTS/GPA_TTS_INT8/model/spark_detokenizer_int8.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04a04ad987486c9affb70af17a2b44f7ca62d14acf00fa512eeb0aff3b297b0
+size 165224448

GPA_TTS/GPA_TTS_INT8/voice/spark_tokenizer_model/config.json

@@ -0,0 +1,83 @@
+{
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "transformers_version": "4.7.0.dev0",
+  "vocab_size": 32
+}

GPA_TTS/GPA_TTS_INT8/voice/spark_tokenizer_model/config.yaml

@@ -0,0 +1,66 @@
+audio_tokenizer:
+  mel_params:
+    sample_rate: 16000
+    n_fft: 1024
+    win_length: 640
+    hop_length: 320
+    mel_fmin: 10 
+    mel_fmax: null
+    num_mels: 128
+
+  encoder:
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 12
+    out_channels: 1024
+    sample_ratios: [1,1]
+
+  decoder:
+    input_channel: 1024
+    channels: 1536
+    rates: [8, 5, 4, 2]
+    kernel_sizes: [16,11,8,4]
+
+  quantizer:
+    input_dim: 1024
+    codebook_size: 8192
+    codebook_dim: 8
+    commitment: 0.25
+    codebook_loss_weight: 2.0
+    use_l2_normlize: True
+    threshold_ema_dead_code: 0.2
+  
+  speaker_encoder:
+    input_dim: 128
+    out_dim: 1024
+    latent_dim: 128
+    token_num: 32
+    fsq_levels: [4, 4, 4, 4, 4, 4]
+    fsq_num_quantizers: 1
+
+  prenet:
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 12
+    out_channels: 1024
+    condition_dim: 1024
+    sample_ratios: [1,1]
+    use_tanh_at_final: False
+
+  postnet: 
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 6
+    out_channels: 1024
+    use_tanh_at_final: False
+highpass_cutoff_freq: 40
+sample_rate: 16000 
+segment_duration: 2.4 # (s)
+max_val_duration: 12 # (s)
+latent_hop_length: 320
+ref_segment_duration: 6
+volume_normalize: true
+

GPA_TTS/GPA_TTS_INT8/voice/spark_tokenizer_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9940cd48d4446e4340ced82d234bf5618350dd9f5db900ebe47a4fdb03867ec
+size 625518756

GPA_TTS/GPA_TTS_INT8/voice/spark_tokenizer_model/wav2vec2-large-xlsr-53/config.json

@@ -0,0 +1,83 @@
+{
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "transformers_version": "4.7.0.dev0",
+  "vocab_size": 32
+}

GPA_TTS/GPA_TTS_INT8/voice/spark_tokenizer_model/wav2vec2-large-xlsr-53/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

GPA_TTS/GPA_TTS_INT8/voice/spark_tokenizer_model/wav2vec2-large-xlsr-53/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314340227371a608f71adcd5f0de5933824fe77e55822aa4b24dba9c1c364dcb
+size 1269737156

GPA_TTS/GPA_TTS_INT8/voices/items/default/global_tokens.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af085e80826c70ba3580c9355ad65084dbd6234c1f9dece87c114e1d3cfe269c
+size 384

GPA_TTS/GPA_TTS_INT8/voices/items/default/meta.json

@@ -0,0 +1,9 @@
+{
+  "name": "default",
+  "voice_id": "default",
+  "created_at": "2026-03-28T15:35:57.789814+00:00",
+  "updated_at": "2026-03-28T15:35:57.790329+00:00",
+  "source_kind": "bundled_reference",
+  "source_label": "038142_global_tokens.npy",
+  "is_default": true
+}

GPA_TTS/GPA_TTS_INT8/voices/registry.json

@@ -0,0 +1,59 @@
+{
+  "version": 1,
+  "voices": [
+    {
+      "name": "default",
+      "voice_id": "default",
+      "created_at": "2026-03-28T15:35:57.789814+00:00",
+      "updated_at": "2026-03-28T15:35:57.790329+00:00",
+      "source_kind": "bundled_reference",
+      "source_label": "038142_global_tokens.npy",
+      "is_default": true
+    },
+    {
+      "name": "linyu-demo",
+      "voice_id": "linyu-demo",
+      "created_at": "2026-03-28T15:40:45.507448+00:00",
+      "updated_at": "2026-03-28T15:40:45.507475+00:00",
+      "source_kind": "upload",
+      "source_label": "dufu.wav",
+      "is_default": false
+    },
+    {
+      "name": "relative_path_check",
+      "voice_id": "relative_path_check",
+      "created_at": "2026-03-28T15:51:09.978360+00:00",
+      "updated_at": "2026-03-28T15:51:09.978384+00:00",
+      "source_kind": "path",
+      "source_label": "038142.wav",
+      "is_default": false
+    },
+    {
+      "name": "smoke_voice",
+      "voice_id": "smoke_voice",
+      "created_at": "2026-03-28T15:36:07.497354+00:00",
+      "updated_at": "2026-03-28T15:36:07.497372+00:00",
+      "source_kind": "path",
+      "source_label": "038142.wav",
+      "is_default": false
+    },
+    {
+      "name": "upload_voice",
+      "voice_id": "upload_voice",
+      "created_at": "2026-03-28T15:38:30.827871+00:00",
+      "updated_at": "2026-03-28T15:38:30.827889+00:00",
+      "source_kind": "upload",
+      "source_label": "038142.wav",
+      "is_default": false
+    },
+    {
+      "name": "曹操",
+      "voice_id": "voice-0e1d3735",
+      "created_at": "2026-03-28T15:52:06.364216+00:00",
+      "updated_at": "2026-03-28T15:52:06.364233+00:00",
+      "source_kind": "upload",
+      "source_label": "（曹操）-皮肤-【奸雄】：宁教我负天下人，休教天下人负我_爱给网_aigei_com.mp3",
+      "is_default": false
+    }
+  ]
+}