End of training

README.md

@@ -2,8 +2,6 @@
 base_model: Edmon02/speecht5_finetuned_voxpopuli_nl
 tags:
 - generated_from_trainer
-datasets:
-- hyvoxpopuli
 model-index:
 - name: speecht5_finetuned_voxpopuli_hy
   results: []
@@ -14,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_voxpopuli_hy
 
-This model is a fine-tuned version of [Edmon02/speecht5_finetuned_voxpopuli_nl](https://huggingface.co/Edmon02/speecht5_finetuned_voxpopuli_nl) on the hyvoxpopuli dataset.
+This model is a fine-tuned version of [Edmon02/speecht5_finetuned_voxpopuli_nl](https://huggingface.co/Edmon02/speecht5_finetuned_voxpopuli_nl) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5655
+- Loss: 0.6466
 
 ## Model description
 
@@ -43,23 +41,22 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 4000
-- mixed_precision_training: Native AMP
+- lr_scheduler_warmup_steps: 125
+- training_steps: 1000
 
 ### Training results
 
-| Training Loss | Epoch     | Step | Validation Loss |
-|:-------------:|:---------:|:----:|:---------------:|
-| 0.5144        | 296.2963  | 1000 | 0.5548          |
-| 0.4797        | 592.5926  | 2000 | 0.5446          |
-| 0.4674        | 888.8889  | 3000 | 0.5519          |
-| 0.4575        | 1185.1852 | 4000 | 0.5655          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.7114        | 2.4600 | 250  | 0.6624          |
+| 0.6999        | 4.9200 | 500  | 0.6542          |
+| 0.7079        | 7.3801 | 750  | 0.6487          |
+| 0.6972        | 9.8401 | 1000 | 0.6466          |
 
 
 ### Framework versions
 
-- Transformers 4.41.2
-- Pytorch 2.3.0+cu121
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

added_tokens.json

@@ -1,4 +1,3 @@
 {
-  "<ctc_blank>": 80,
-  "<mask>": 79
+  "<pad>": 157
 }

config.json

@@ -65,8 +65,8 @@
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
   "max_length": 1876,
-  "max_speech_positions": 1876,
-  "max_text_positions": 600,
+  "max_speech_positions": 5000,
+  "max_text_positions": 512,
   "model_type": "speecht5",
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
@@ -85,8 +85,8 @@
   "speech_decoder_prenet_layers": 2,
   "speech_decoder_prenet_units": 256,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.42.4",
   "use_cache": false,
   "use_guided_attention_loss": true,
-  "vocab_size": 81
+  "vocab_size": 158
 }

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.42.4"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a9e46e706ed75385aa87712c5521d64a17e1892d4fd63a1d07144e3326cfaa3
-size 577789320
+oid sha256:9bcf0a24f4e638b8747787afb342716c35f1d34be8e4ad482af745987e20edfc
+size 578025864

runs/Jul27_10-54-15_caa53b8840ec/events.out.tfevents.1722077676.caa53b8840ec.310.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd5ef7b517d7c76867a8830882d101b412770f06b2b7b024322bac4737861ce0
+size 42741

runs/Jul27_11-53-20_caa53b8840ec/events.out.tfevents.1722081204.caa53b8840ec.16745.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b574ee8c843d3ab268ba71ce8127660ba0d0e240134c50d902097657ffe147
+size 42909

special_tokens_map.json

@@ -1,13 +1,6 @@
 {
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
   "pad_token": "<pad>",
   "unk_token": "<unk>"
 }

spm_char.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
-size 238473
+oid sha256:b5f1ed236bbb46e584fad7dc1e93e7dcae275eda86e53ed80365bf5531ebc41b
+size 239298

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -24,36 +24,19 @@
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "157": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "79": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "80": {
-      "content": "<ctc_blank>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "model_max_length": 600,
+  "model_max_length": 1000000000000000019884624838656,
   "normalize": false,
   "pad_token": "<pad>",
   "processor_class": "SpeechT5Processor",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923a08646dc770d432227f22698377c2adcfd47e3021a435b4577c2c85fda902
+oid sha256:7a12c0040b3a2d22c02d61dbedce1862573e49552d1b47c121c84008c2c0b45d
 size 5304