End of training

README.md

@@ -4,6 +4,8 @@ license: mit
 base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
+datasets:
+- fleurs
 model-index:
 - name: speecht5_finetuned_uz
   results: []
@@ -14,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_uz
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the fleurs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4840
 
 ## Model description
 
@@ -39,19 +43,26 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 64
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 3
+- training_steps: 5000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch    | Step | Validation Loss |
+|:-------------:|:--------:|:----:|:---------------:|
+| 3.3727        | 24.3902  | 1000 | 0.4688          |
+| 3.2448        | 48.7805  | 2000 | 0.4741          |
+| 3.1413        | 73.1707  | 3000 | 0.4736          |
+| 3.0824        | 97.5610  | 4000 | 0.4806          |
+| 3.1047        | 121.9512 | 5000 | 0.4840          |
 
 
 ### Framework versions
 
 - Transformers 4.47.1
-- Pytorch 2.5.1+cu124
-- Datasets 3.2.0
+- Pytorch 2.2.2+cu121
+- Datasets 3.1.0
 - Tokenizers 0.21.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0d5f69116ada1f57c8962d0e16f0ae9c382d5b1705da1bbc88710139291864c
+oid sha256:ea0f926d27081f861f62d07efea8c3498bf9e5b38396e1cbd43b4c46ebde0965
 size 577789320

runs/Dec22_11-16-05_ai/events.out.tfevents.1734866170.ai.2967859.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def7dbd8c07b1bad3a6b4a766c7fd27713592fdfaa4c11e34743ba40e9581b59
+size 7860

runs/Dec22_12-13-24_ai/events.out.tfevents.1734869607.ai.3006405.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c209e67266e7f798a3d947f92f4eec9dc9da15b14353355b57934839cce58764
+size 6684

runs/Dec22_12-13-50_ai/events.out.tfevents.1734869631.ai.3006405.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8a888d6b891b54b69d23fb83b4d92b63847d970eb5decf498a2dd79e77dbc5
+size 6685

runs/Dec22_12-15-42_ai/events.out.tfevents.1734869743.ai.3008980.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97772096402ca38d2c01dd1007441fcfc9f4f88e04bb564c9ebe00c768259d1
+size 21005

runs/Dec24_11-19-25_ai/events.out.tfevents.1735039170.ai.3953637.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe3aafac76f88ed161e3452b3829414e662738b4a00e6c42bfae566aae6c575
+size 50577

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5293acca38e6d9e40cd550564a6d500782b3a3af7f71da1f1cda70a4cf05ed0
+oid sha256:a2a49a2f1869549ff2984b7c702b317306cfac1bdd88723aca949e70017cc672
 size 5496