Duplicate from onnx-community/pyannote-segmentation-3.0

Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>

.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

README.md

@@ -0,0 +1,93 @@
+---
+base_model: pyannote/segmentation-3.0
+library_name: transformers.js
+license: mit
+---
+
+https://huggingface.co/pyannote/segmentation-3.0 with ONNX weights to be compatible with Transformers.js.
+
+
+## Transformers.js (v3) usage
+
+```js
+import { AutoProcessor, AutoModelForAudioFrameClassification, read_audio } from '@huggingface/transformers';
+
+// Load model and processor
+const model_id = 'onnx-community/pyannote-segmentation-3.0';
+const model = await AutoModelForAudioFrameClassification.from_pretrained(model_id);
+const processor = await AutoProcessor.from_pretrained(model_id);
+
+// Read and preprocess audio
+const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/mlk.wav';
+const audio = await read_audio(url, processor.feature_extractor.config.sampling_rate);
+const inputs = await processor(audio);
+
+// Run model with inputs
+const { logits } = await model(inputs);
+// {
+//   logits: Tensor {
+//     dims: [ 1, 767, 7 ],  // [batch_size, num_frames, num_classes]
+//     type: 'float32',
+//     data: Float32Array(5369) [ ... ],
+//     size: 5369
+//   }
+// }
+
+const result = processor.post_process_speaker_diarization(logits, audio.length);
+// [
+//   [
+//     { id: 0, start: 0, end: 1.0512535626298245, confidence: 0.8220156481664611 },
+//     { id: 2, start: 1.0512535626298245, end: 2.3398869619825127, confidence: 0.9008811707860472 },
+//     ...
+//   ]
+// ]
+
+// Display result
+console.table(result[0], ['start', 'end', 'id', 'confidence']);
+// ┌─────────┬────────────────────┬────────────────────┬────┬─────────────────────┐
+// │ (index) │ start              │ end                │ id │ confidence          │
+// ├─────────┼────────────────────┼────────────────────┼────┼─────────────────────┤
+// │ 0       │ 0                  │ 1.0512535626298245 │ 0  │ 0.8220156481664611  │
+// │ 1       │ 1.0512535626298245 │ 2.3398869619825127 │ 2  │ 0.9008811707860472  │
+// │ 2       │ 2.3398869619825127 │ 3.5946089560890773 │ 0  │ 0.7521651315796233  │
+// │ 3       │ 3.5946089560890773 │ 4.578039708226655  │ 2  │ 0.8491978128022479  │
+// │ 4       │ 4.578039708226655  │ 4.594995410849717  │ 0  │ 0.2935352600416393  │
+// │ 5       │ 4.594995410849717  │ 6.121008646925269  │ 3  │ 0.6788051309866024  │
+// │ 6       │ 6.121008646925269  │ 6.256654267909762  │ 0  │ 0.37125512393851134 │
+// │ 7       │ 6.256654267909762  │ 8.630452635138397  │ 2  │ 0.7467035186353542  │
+// │ 8       │ 8.630452635138397  │ 10.088643060721703 │ 0  │ 0.7689364814666032  │
+// │ 9       │ 10.088643060721703 │ 12.58113134631177  │ 2  │ 0.9123324509131324  │
+// │ 10      │ 12.58113134631177  │ 13.005023911888312 │ 0  │ 0.4828358177572041  │
+// └─────────┴────────────────────┴────────────────────┴────┴─────────────────────┘
+```
+
+## Torch → ONNX conversion code:
+```py
+# pip install torch onnx https://github.com/pyannote/pyannote-audio/archive/refs/heads/develop.zip
+import torch
+from pyannote.audio import Model
+
+model = Model.from_pretrained(
+  "pyannote/segmentation-3.0", 
+  use_auth_token="hf_...", # <-- Set your HF token here
+).eval()
+
+dummy_input = torch.zeros(2, 1, 160000)
+torch.onnx.export(
+    model,
+    dummy_input,
+    'model.onnx',
+    do_constant_folding=True,
+    input_names=["input_values"],
+    output_names=["logits"],
+    dynamic_axes={
+        "input_values": {0: "batch_size", 1: "num_channels", 2: "num_samples"},
+        "logits": {0: "batch_size", 1: "num_frames"},
+    },
+)
+```
+
+---
+
+
+Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

config.json

@@ -0,0 +1,21 @@
+{
+  "model_type": "pyannote",
+  "id2label": {
+    "0": "NO_SPEAKER",
+    "1": "SPEAKER_1",
+    "2": "SPEAKER_2",
+    "3": "SPEAKER_3",
+    "4": "SPEAKERS_1_AND_2",
+    "5": "SPEAKERS_1_AND_3",
+    "6": "SPEAKERS_2_AND_3"
+  },
+  "label2id": {
+    "NO_SPEAKER": 0,
+    "SPEAKER_1": 1,
+    "SPEAKER_2": 2,
+    "SPEAKER_3": 3,
+    "SPEAKERS_1_AND_2": 4,
+    "SPEAKERS_1_AND_3": 5,
+    "SPEAKERS_2_AND_3": 6
+  }
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057ee564753071c0b09b5b611648b50ac188d50846bff5f01e9f7bbf1591ea25
+size 5986908

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1068e7f01b47e5410b232399f02890f61e95897313daac1bfe0d6a3307134fcc
+size 5815342

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3dba0c91270b923e9ce66e4cef123820cb73c9b07e47e03a3d7d4267e4fbec4
+size 3000918

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465d0975bf70fbf14fb77c0589a5d346a9c07c2170345f529cf774678446db76
+size 1542304

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b0462cd3555b183e8845d37f372d9be2c0dd9a04ce79991b361186cf4d23ac
+size 5818448

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5664adf52a5637fb3785608772ca0d34c31911f96c4f48b3cebda0fb6f2c7ed
+size 2929425

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a3eb106923c9b76a7d8af07ac337dd24c2d0dcd20f1b6c55f21133e944d658
+size 1542308

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a3eb106923c9b76a7d8af07ac337dd24c2d0dcd20f1b6c55f21133e944d658
+size 1542308

preprocessor_config.json

@@ -0,0 +1,7 @@
+{
+  "feature_extractor_type": "PyAnnoteFeatureExtractor",
+  "processor_class": "PyAnnoteProcessor",
+  "offset": 990,
+  "sampling_rate": 16000,
+  "step": 270
+}