Final model after training with pause augmentation

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+tags:
+- audio-classification
+- turn-detection
+- hindi
+- generated_from_trainer
+model-index:
+- name: hindi-turn-detector-with-random-pauses
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# hindi-turn-detector-with-random-pauses
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 40
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.16.1
+- Pytorch 2.11.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.23.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "augmented_accuracy": 0.5095,
+    "augmented_f1": 0.6746268656716418,
+    "augmented_loss": 0.6926261782646179,
+    "augmented_precision": 0.509009009009009,
+    "augmented_recall": 1.0,
+    "clean_accuracy": 0.5095,
+    "clean_f1": 0.6746268656716418,
+    "clean_loss": 0.6926307082176208,
+    "clean_precision": 0.509009009009009,
+    "clean_recall": 1.0
+}

augmented_results.json

@@ -0,0 +1,7 @@
+{
+    "augmented_accuracy": 0.5095,
+    "augmented_f1": 0.6746268656716418,
+    "augmented_loss": 0.6926261782646179,
+    "augmented_precision": 0.509009009009009,
+    "augmented_recall": 1.0
+}

clean_results.json

@@ -0,0 +1,7 @@
+{
+    "clean_accuracy": 0.5095,
+    "clean_f1": 0.6746268656716418,
+    "clean_loss": 0.6926307082176208,
+    "clean_precision": 0.509009009009009,
+    "clean_recall": 1.0
+}

config.json

@@ -0,0 +1,11 @@
+{
+  "architectures": [
+    "TurnDetector"
+  ],
+  "dtype": "float32",
+  "hidden_size": 384,
+  "model_type": "turn_detector",
+  "transformers_version": "5.16.1",
+  "use_cache": false,
+  "whisper_model_name": "openai/whisper-tiny"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9ee887c53dc8a8d0137f8137b8a6530729da7a61ff21fa65f8f74db00a05a1
+size 32009584

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 8,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 128000,
+  "nb_max_frames": 800,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015f1873fc64f0031b7d96df8e4903969be61f0ea7a1e434b83646fdb3fbb8c3
+size 5265