End of training

README.md

@@ -14,8 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
 # malay_micro_checkpoint
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.7351
 
 ## Model description
 
@@ -44,13 +42,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.0097        | 0.56  | 500  | 0.8714          |
-| 0.9306        | 1.11  | 1000 | 0.8210          |
-| 0.8819        | 1.67  | 1500 | 0.7571          |
-| 0.8302        | 2.22  | 2000 | 0.7460          |
-| 0.8073        | 2.78  | 2500 | 0.7351          |
 
 
 ### Framework versions

config.json

@@ -86,7 +86,7 @@
   "speech_decoder_prenet_units": 256,
   "torch_dtype": "float32",
   "transformers_version": "4.40.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "use_guided_attention_loss": true,
   "vocab_size": 81
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3375dc2e621120001b4d1d3fc5b1a8b6b2fca27c376fd9f54df7b11f5a6cccdd
+oid sha256:1b4196812139facae97097dd0cdcde42ae72e98a24499e1f900f2ea05ed9a83d
 size 577789320

runs/Apr03_17-22-56_5a5eb73bab84/events.out.tfevents.1712164977.5a5eb73bab84.461.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c644faa0a1c7e3e91beac4c22b8147c5785dff2b0ba4812fa68e4e553d2db14c
+size 6710

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:515e68ef4937bf3fdd1be584f1d2c2806c03e709144740e4f67f585454d92f23
+oid sha256:d45ce8c59d9b4dc0031463b3db134ae238556341a797737d48c85782e392e20c
 size 5176