Add ONNX models (INT8 + FP32) and config

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+library_name: onnxruntime
+base_model: prithivMLmods/Speech-Emotion-Classification
+tags:
+  - audio-classification
+  - speech-emotion-recognition
+  - wav2vec2
+  - onnx
+  - chotko
+language:
+  - en
+pipeline_tag: audio-classification
+---
+
+# Speech Emotion Classification — ONNX (INT8)
+
+ONNX INT8-quantized version of [prithivMLmods/Speech-Emotion-Classification](https://huggingface.co/prithivMLmods/Speech-Emotion-Classification) for on-device inference in macOS apps via ONNX Runtime C API.
+
+## Model Details
+
+- **Architecture:** Wav2Vec2ForSequenceClassification (facebook/wav2vec2-base-960h fine-tuned)
+- **Format:** ONNX INT8 quantized
+- **Size:** ~91 MB (INT8), ~361 MB (FP32)
+- **Input:** Raw audio waveform (16kHz, mono), shape `[1, num_samples]`
+- **Output:** 8-class emotion logits
+
+### Emotion Labels
+
+| ID | Label | Full |
+|----|-------|------|
+| 0 | ANG | Anger |
+| 1 | CAL | Calm |
+| 2 | DIS | Disgust |
+| 3 | FEA | Fear |
+| 4 | HAP | Happy |
+| 5 | NEU | Neutral |
+| 6 | SAD | Sad |
+| 7 | SUR | Surprised |
+
+## Usage
+
+Used in [Chotko](https://github.com/smkrv/Chotko) macOS app for real-time speech emotion classification during transcription. Inference via ONNX Runtime C API (bundled with Sherpa-ONNX).
+
+```swift
+// Swift — load and run via OnnxRuntimeWrapper
+let wrapper = OnnxRuntimeWrapper()
+try wrapper.load(modelPath: "model_int8.onnx")
+let logits = try wrapper.run(inputName: "input_values", inputData: audioBuffer, inputShape: [1, Int64(audioBuffer.count)])
+let emotionIdx = logits.firstIndex(of: logits.max()!)!
+```
+
+## Files
+
+- `model_int8.onnx` — INT8 quantized model (recommended for on-device use)
+- `model.onnx` — FP32 full precision model
+- `config.json` — Model configuration with label mappings
+
+## Attribution
+
+Original model by [prithivMLmods](https://huggingface.co/prithivMLmods). Converted to ONNX by [onnx-community](https://huggingface.co/onnx-community). INT8 quantization and packaging for macOS by [@smkrv](https://huggingface.co/smkrv).

fp32/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

fp32/README.md

@@ -0,0 +1,23 @@
+---
+library_name: transformers.js
+base_model:
+- prithivMLmods/Speech-Emotion-Classification
+---
+
+# Speech-Emotion-Classification (ONNX)
+
+This is an ONNX version of [prithivMLmods/Speech-Emotion-Classification](https://huggingface.co/prithivMLmods/Speech-Emotion-Classification). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
+
+# Speech-Emotion-Classification
+
+> **Speech-Emotion-Classification** is a fine-tuned version of `facebook/wav2vec2-base-960h` for **multi-class audio classification**, specifically trained to detect **emotions** in speech. This model utilizes the `Wav2Vec2ForSequenceClassification` architecture to accurately classify speaker emotions from audio signals.
+
+## Intended Use
+
+`Speech-Emotion-Classification` is designed for:
+
+* **Speech Emotion Analytics** – Analyze speaker emotions in call centers, interviews, or therapeutic sessions.
+* **Conversational AI Personalization** – Adjust voice assistant responses based on detected emotion.
+* **Mental Health Monitoring** – Support emotion recognition in voice-based wellness or teletherapy apps.
+* **Voice Dataset Curation** – Tag or filter speech datasets by emotion for research or model training. 
+* **Media Annotation** – Automatically annotate podcasts, audiobooks, or videos with speaker emotion metadata.

fp32/config.json

@@ -0,0 +1,139 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "prithivMLmods/Speech-Emotion-Classification",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ANG",
+    "1": "CAL",
+    "2": "DIS",
+    "3": "FEA",
+    "4": "HAP",
+    "5": "NEU",
+    "6": "SAD",
+    "7": "SUR"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ANG": 0,
+    "CAL": 1,
+    "DIS": 2,
+    "FEA": 3,
+    "HAP": 4,
+    "NEU": 5,
+    "SAD": 6,
+    "SUR": 7
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

fp32/onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b8bf484dd54512fd5c278ac27ab176c0e82a48a82d008a85dcbeaceaadfda0
+size 378609481

fp32/onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e885dffd59cbd307854d3ba5e97a85da47b0272b10c699f3ecfc082503fdd4c8
+size 84630595

fp32/onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f76a2072399be11130e0e89c0b715cbc2fa1273b044a6ec06e9b03bae448d33
+size 189468010

fp32/onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1720a40017ecd8d71bc41988b115bd9d96cfdf796c127268b2afa1302473632f
+size 95389021

fp32/onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4b907c758b975a64a60af2c54902bfa5ddf5e3993463f388fae84cfff3d3a8
+size 89975333

fp32/onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8f8da326aafd658e7934e0c489a3c77165a66142ee19fe561733e94543bed7
+size 66537637

fp32/onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3217e95e4b28d53913fbe94cd9650b520f8e7ecf2bd643b9e45fc5b8b93b8aab
+size 95389059

fp32/onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3217e95e4b28d53913fbe94cd9650b520f8e7ecf2bd643b9e45fc5b8b93b8aab
+size 95389059

fp32/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

fp32/quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": false,
+    "reduce_range": false,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}