End of training

README.md

@@ -1,24 +1,24 @@
 ---
 library_name: transformers
 language:
-- eng
+- hi
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- Trelis/llm-lingo
+- mozilla-foundation/common_voice_11_0
 model-index:
-- name: Whisper fine tuned model-HK
+- name: Whisper Small Hi - Harshith Kethineni
   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. -->
 
-# Whisper fine tuned model-HK
+# Whisper Small Hi - Harshith Kethineni
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Trelis/llm-lingo dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 
 ## Model description
 
@@ -38,13 +38,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
+- train_batch_size: 24
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 48
 - optimizer: Use adamw_torch 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: 500
-- training_steps: 50
+- lr_scheduler_warmup_steps: 200
+- training_steps: 5
 - mixed_precision_training: Native AMP
 
 ### Training results

generation_config.json

@@ -150,7 +150,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "english",
+  "language": "hindi",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,