End of training

README.md

@@ -1,41 +1,41 @@
 ---
 language:
-- te
+- hi
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_17_0
+- mozilla-foundation/common_voice_11_0
 metrics:
 - wer
 model-index:
-- name: Whisper Small Telugu - Mukund Vahinipathi
+- name: Whisper Small Hi - Mukund Vahinipathi
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice 17.0
-      type: mozilla-foundation/common_voice_17_0
-      config: te
+      name: Common Voice 11.0
+      type: mozilla-foundation/common_voice_11_0
+      config: hi
       split: None
       args: 'config: hi, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 85.16483516483517
+      value: 32.77321594853128
 ---
 
 <!-- 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 Small Telugu - Mukund Vahinipathi
+# Whisper Small Hi - Mukund Vahinipathi
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 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.
 It achieves the following results on the evaluation set:
-- Loss: 1.0586
-- Wer: 85.1648
+- Loss: 0.4415
+- Wer: 32.7732
 
 ## Model description
 
@@ -66,12 +66,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch    | Step | Validation Loss | Wer     |
-|:-------------:|:--------:|:----:|:---------------:|:-------:|
-| 0.0           | 142.8571 | 1000 | 0.8112          | 85.1648 |
-| 0.0           | 285.7143 | 2000 | 0.9179          | 85.1648 |
-| 0.0           | 428.5714 | 3000 | 1.0129          | 85.7143 |
-| 0.0           | 571.4286 | 4000 | 1.0586          | 85.1648 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.0917        | 2.4450 | 1000 | 0.2977          | 34.9149 |
+| 0.0207        | 4.8900 | 2000 | 0.3538          | 33.8356 |
+| 0.0013        | 7.3350 | 3000 | 0.4184          | 32.7521 |
+| 0.0005        | 9.7800 | 4000 | 0.4415          | 32.7732 |
 
 
 ### Framework versions

generation_config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e6297c604937bca4b5dece2d896f4db19deba278683f302460bef64428d1d9
+oid sha256:09b609d46f84597e95b1968b6f12ede0463b68f519ca5848b0753b73f85728f8
 size 966995080

runs/May05_05-51-03_373f71ce7a46/events.out.tfevents.1714888383.373f71ce7a46.953.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5b0cf6b694740d6236fd6beab4aaf50fe895afe0bb2e85fcb80ecae7eed94a
-size 41457
+oid sha256:e2a7065fec1ae541f0344b74489e098cf80f2014d6b60c0cfffd62c10b8f55ac
+size 41811