Model save

README.md

@@ -1,6 +1,4 @@
 ---
-language:
-- en
 license: apache-2.0
 base_model: openai/whisper-medium.en
 tags:
@@ -8,20 +6,20 @@ tags:
 metrics:
 - wer
 model-index:
-- name: ./500
+- name: whisper-medium.en-cit-do015-wd0-lr1e-06-SF-500
   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. -->
 
-# ./500
+# whisper-medium.en-cit-do015-wd0-lr1e-06-SF-500
 
-This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the 500 SF 1000 dataset.
+This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7070
-- Wer Ortho: 28.9359
-- Wer: 18.7657
+- Loss: 0.6792
+- Wer Ortho: 31.5962
+- Wer: 21.0621
 
 ## Model description
 
@@ -50,18 +48,21 @@ 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: 200
-- training_steps: 500
+- training_steps: 800
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:---------:|:-------:|
-| 1.6528        | 3.1746  | 100  | 1.1367          | 40.6706   | 29.8170 |
-| 0.8589        | 6.3492  | 200  | 0.7969          | 30.5029   | 20.0215 |
-| 0.6147        | 9.5238  | 300  | 0.7363          | 28.9359   | 18.7298 |
-| 0.5156        | 12.6984 | 400  | 0.7134          | 28.7536   | 18.8375 |
-| 0.4706        | 15.8730 | 500  | 0.7070          | 28.9359   | 18.7657 |
+| 1.6525        | 3.1746  | 100  | 1.1367          | 40.1968   | 29.4223 |
+| 0.8573        | 6.3492  | 200  | 0.7964          | 30.8309   | 20.3803 |
+| 0.6108        | 9.5238  | 300  | 0.7344          | 28.6808   | 18.9092 |
+| 0.4957        | 12.6984 | 400  | 0.7017          | 29.1181   | 18.7298 |
+| 0.4164        | 15.8730 | 500  | 0.6860          | 29.2274   | 18.8016 |
+| 0.3577        | 19.0476 | 600  | 0.6802          | 29.3367   | 18.6939 |
+| 0.3168        | 22.2222 | 700  | 0.6787          | 31.2682   | 20.7750 |
+| 0.3023        | 25.3968 | 800  | 0.6792          | 31.5962   | 21.0621 |
 
 
 ### Framework versions

config.json

@@ -2,7 +2,7 @@
   "_name_or_path": "openai/whisper-medium.en",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "apply_spec_augment": true,
+  "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
@@ -19,7 +19,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 24,
   "decoder_start_token_id": 50257,
-  "dropout": 0.15,
+  "dropout": 0,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aefc7727c6b4fe9e86a1254732ec32aad51f2a19cde18606cbabad6f5062a9c2
+oid sha256:acb7f41aba117bc950bd3e956c7faf341008175efaafa743036f7cbc3bbb50b5
 size 1634043280

runs/Aug13_17-06-44_whisper-finetuning/events.out.tfevents.1723568822.whisper-finetuning

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85837d03761a167783e99e67d6d4892ea14f42c479b9b4d057544e0562ffe0a2
-size 11003
+oid sha256:3491464321f458ea77914a77ca4c30758feddb3872f463f50c53b36006785e22
+size 11728