Model save

README.md

@@ -1,7 +1,5 @@
 ---
 library_name: transformers
-language:
-- en
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
@@ -9,19 +7,19 @@ tags:
 metrics:
 - wer
 model-index:
-- name: Whisper-squeezeformer-NSQU-whisper-sparse-A
+- name: Whisper-squeezeformer-v4
   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-squeezeformer-NSQU-whisper-sparse-A
+# Whisper-squeezeformer-v4
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the LibriSpeech dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1838
-- Wer: 9.5918
+- Loss: 0.1860
+- Wer: 9.1296
 
 ## Model description
 
@@ -47,7 +45,7 @@ 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: 3000
-- training_steps: 30000
+- training_steps: 36000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -64,6 +62,8 @@ The following hyperparameters were used during training:
 | 0.2177        | 9.6   | 24000 | 0.1991          | 10.8624  |
 | 0.127         | 10.8  | 27000 | 0.1856          | 10.5485  |
 | 0.0909        | 12.0  | 30000 | 0.1838          | 9.5918   |
+| 0.0785        | 13.2  | 33000 | 0.1849          | 9.1030   |
+| 0.0595        | 14.4  | 36000 | 0.1860          | 9.1296   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063b5880049e5555fdea591fdf2c599d666b193f7d97a107dda0ccb96ec610fb
+oid sha256:39c8fcaf8a73d5c00a8abf49a6ed129fff658bbe1c631db76d1f7ed529a3035f
 size 1128325080