Upload fine-tuned Bengali speaker diarization model

README.md

@@ -0,0 +1,32 @@
+---
+language:
+- bn
+tags:
+- speaker-diarization
+- pyannote
+- pyannote-audio
+- audio
+- voice
+- speech
+- bengali
+license: mit
+datasets:
+- custom
+metrics:
+- der
+model-index:
+- name: bengali-speaker-diarization_v1
+  results:
+  - task:
+      type: speaker-diarization
+      name: Speaker Diarization
+    metrics:
+    - type: der
+      value: Not computed
+      name: Diarization Error Rate
+---
+
+# bengali-speaker-diarization_v1
+
+This is a fine-tuned speaker diarization model based on pyannote.audio, specifically trained on Bengali audio data.
+

USAGE.md

@@ -0,0 +1,4 @@
+# Example Usage: bengali-speaker-diarization_v1
+
+This example shows how to use the model for speaker diarization.
+

config.yaml

@@ -0,0 +1,16 @@
+
+# Model configuration for pyannote.audio
+task:
+  name: SpeakerDiarization
+  
+architecture:
+  name: PyanNet
+  
+specifications:
+  duration: 5.0
+  sample_rate: 16000
+  
+training:
+  batch_size: 32
+  learning_rate: 0.0001
+  max_epochs: 20

pipeline_config.json

@@ -0,0 +1,16 @@
+{
+  "model_type": "speaker-diarization",
+  "pyannote_version": "3.3.2",
+  "embedding_model": "pyannote/wespeaker-voxceleb-resnet34-LM",
+  "optimal_parameters": {
+    "segmentation": {
+      "threshold": 0.5,
+      "min_duration_off": 0.0
+    },
+    "clustering": {
+      "method": "centroid",
+      "threshold": 0.7,
+      "min_cluster_size": 12
+    }
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb89ca4e8ffeda8f86576af8c86fb0ee173aa1f1cb24820abe6d4b9b42402b77
+size 17733969