End of training

README.md

@@ -2,7 +2,7 @@
 language:
 - hi
 license: apache-2.0
-base_model: openai/whisper-large-v3
+base_model: quinnb/whisper-Large-v3-hindi
 tags:
 - generated_from_trainer
 datasets:
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Large v3 Trained on Hindi
 
-This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 17.0 dataset.
+This model is a fine-tuned version of [quinnb/whisper-Large-v3-hindi](https://huggingface.co/quinnb/whisper-Large-v3-hindi) on the Common Voice 17.0 dataset.
 
 ## Model description
 
@@ -37,17 +37,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
-- eval_batch_size: 64
+- train_batch_size: 1
+- eval_batch_size: 16
 - seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
 - gradient_accumulation_steps: 16
 - total_train_batch_size: 64
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 5000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.41.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-large-v3",
+  "_name_or_path": "quinnb/whisper-Large-v3-hindi",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -42,7 +42,7 @@
   "num_mel_bins": 128,
   "pad_token_id": 50256,
   "scale_embedding": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.41.1",
   "use_cache": true,
   "use_weighted_layer_sum": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02fde508dec44d0cbb27ad745f11c77a2b742eaecb29d3ff60bc4191c846f9b
+oid sha256:d1ff3694f9fa53a69eba7760ad5fbad10174a1c715a461eaee7b275df55e6f3e
 size 3219908024

runs/May31_01-34-01_bhrathgpt-v1/events.out.tfevents.1717119265.bhrathgpt-v1.1840323.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378ae266fc3eb9126b0c42b496a98a9dd88ee58415d98a07d6981475e4ac71ff
+size 5616

runs/May31_01-38-23_bhrathgpt-v1/events.out.tfevents.1717119524.bhrathgpt-v1.1841996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845b205994f49a9b6e665ca08a08f27b9172c8e99d514ce4af4cf57cca933744
+size 22832

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34facea37d4705d15a4fdc1db99d081ec602439fc3e74151978af6c6ac17b08e
-size 4783
+oid sha256:3be1cc8c0ac887ec1ab6d0469bb80e0bf977a2e7ee3554593ef4f6ad601191b3
+size 5615