End of training

README.md

@@ -1,11 +1,14 @@
 ---
 library_name: transformers
+language:
+- hi
 license: mit
 base_model: microsoft/speecht5_tts
 tags:
+- Hindi
 - generated_from_trainer
 datasets:
-- common_voice_17_0
+- mozilla-foundation/common_voice_17_0
 model-index:
 - name: Speect5-common-voice-Hindi
   results: []
@@ -18,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4767
+- Loss: 0.4779
 
 ## Model description
 
@@ -53,14 +56,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.644         | 0.3445 | 100  | 0.5838          |
-| 0.5903        | 0.6891 | 200  | 0.5449          |
-| 0.5611        | 1.0336 | 300  | 0.5163          |
-| 0.5446        | 1.3781 | 400  | 0.5091          |
-| 0.5399        | 1.7227 | 500  | 0.4958          |
-| 0.533         | 2.0672 | 600  | 0.4923          |
-| 0.5207        | 2.4117 | 700  | 0.4808          |
-| 0.511         | 2.7562 | 800  | 0.4767          |
+| 0.6641        | 0.4522 | 100  | 0.5698          |
+| 0.599         | 0.9045 | 200  | 0.5364          |
+| 0.5628        | 1.3567 | 300  | 0.5207          |
+| 0.5408        | 1.8089 | 400  | 0.4970          |
+| 0.5262        | 2.2612 | 500  | 0.4863          |
+| 0.5205        | 2.7134 | 600  | 0.4779          |
 
 
 ### Framework versions

runs/Oct15_09-32-15_c7070c88f394/events.out.tfevents.1728984738.c7070c88f394.864.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a23b10c6bb2c4ad40b702b7cdd2d4424e31ace72404a7ec2560c1db31352879
-size 13313
+oid sha256:37acf9dd61c3642a5bc20946bfe5ea2d3fef95b1d62fc9100f6de06e5bfa469a
+size 14089