Model save

README.md

@@ -1,42 +1,39 @@
 ---
-language:
-- ml
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
-- whisper-event
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_16_0
+- common_voice_16_0
 metrics:
 - wer
 model-index:
-- name: Breeze DSW Malayalam - tiny
+- name: breeze-dsw-tiny-ml
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: mozilla-foundation/common_voice_16_0 ml
-      type: mozilla-foundation/common_voice_16_0
+      name: common_voice_16_0
+      type: common_voice_16_0
       config: ml
       split: test
       args: ml
     metrics:
     - name: Wer
       type: wer
-      value: 54.37442075996293
+      value: 55.097312326227986
 ---
 
 <!-- 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. -->
 
-# Breeze DSW Malayalam - tiny
+# breeze-dsw-tiny-ml
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the mozilla-foundation/common_voice_16_0 ml dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_16_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5503
-- Wer: 54.3744
+- Loss: 0.7383
+- Wer: 55.0973
 
 ## Model description
 
@@ -63,7 +60,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 1000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results

runs/Jan16_19-35-52_knight/events.out.tfevents.1705430208.knight.101460.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c58289497108520808d982c4044e83e2d972c5a51e06d611f6d21da0fde1e3e
+size 5811

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7bec5b47d1ddacc9840b0c0c8c1f8bbde7d7fed79dd3fc7a7d3e89f01cef9f
+oid sha256:d3e435c0fbea63cf3aeb38f0b1876c2e4d2c8aee3319eadf819a5b65eabc839e
 size 6712