Model save

README.md

@@ -1,7 +1,5 @@
 ---
 library_name: peft
-language:
-- fr
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
@@ -11,19 +9,19 @@ tags:
 metrics:
 - wer
 model-index:
-- name: 52Hz Small Fr - IMT Atlantique X 52 Hertz
+- name: 52Hz-small-LORA-fr
   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. -->
 
-# 52Hz Small Fr - IMT Atlantique X 52 Hertz
+# 52Hz-small-LORA-fr
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Premier dataset organisé de 52 Hertz 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: 0.4195
-- Wer: 30.9701
+- Loss: 0.3461
+- Wer: 29.8507
 
 ## Model description
 
@@ -56,23 +54,23 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer      |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.1006        | 1.0   | 21   | 1.2721          | 105.4104 |
-| 2.2874        | 2.0   | 42   | 1.0456          | 66.2313  |
-| 1.7492        | 3.0   | 63   | 0.8937          | 48.3209  |
-| 1.3342        | 4.0   | 84   | 0.7667          | 41.9776  |
-| 1.2077        | 5.0   | 105  | 0.6449          | 40.2985  |
-| 0.9589        | 6.0   | 126  | 0.5599          | 38.0597  |
-| 0.7839        | 7.0   | 147  | 0.5035          | 36.5672  |
-| 0.7234        | 8.0   | 168  | 0.4723          | 34.1418  |
-| 0.7393        | 9.0   | 189  | 0.4509          | 31.9030  |
-| 0.6897        | 10.0  | 210  | 0.4393          | 31.7164  |
-| 0.5942        | 11.0  | 231  | 0.4300          | 30.9701  |
-| 0.6358        | 12.0  | 252  | 0.4241          | 31.3433  |
-| 0.6393        | 13.0  | 273  | 0.4206          | 30.9701  |
-| 0.6211        | 14.0  | 294  | 0.4196          | 30.9701  |
-| 0.6026        | 15.0  | 315  | 0.4195          | 30.9701  |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 2.9259        | 1.0   | 21   | 1.1730          | 70.5224 |
+| 1.8966        | 2.0   | 42   | 0.9073          | 47.3881 |
+| 1.3732        | 3.0   | 63   | 0.7192          | 41.0448 |
+| 0.9515        | 4.0   | 84   | 0.5480          | 38.0597 |
+| 0.8467        | 5.0   | 105  | 0.4615          | 33.2090 |
+| 0.6615        | 6.0   | 126  | 0.4187          | 32.6493 |
+| 0.5408        | 7.0   | 147  | 0.3862          | 31.1567 |
+| 0.4857        | 8.0   | 168  | 0.3715          | 30.0373 |
+| 0.5076        | 9.0   | 189  | 0.3638          | 30.0373 |
+| 0.4837        | 10.0  | 210  | 0.3582          | 30.0373 |
+| 0.4008        | 11.0  | 231  | 0.3522          | 29.6642 |
+| 0.4278        | 12.0  | 252  | 0.3485          | 29.4776 |
+| 0.4311        | 13.0  | 273  | 0.3465          | 29.8507 |
+| 0.4184        | 14.0  | 294  | 0.3462          | 29.8507 |
+| 0.4092        | 15.0  | 315  | 0.3461          | 29.8507 |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:237815af3d45ef0a697649b2ad114cd172fd879def586ba89f899ef0971d55fe
+oid sha256:d3e049730922ae8a4dd29f5181c8c125d3448de5bc7d59cca709e98f053ebd16
 size 103862440