Training in progress, step 1000

config.json

@@ -85,7 +85,7 @@
   "speech_decoder_prenet_layers": 2,
   "speech_decoder_prenet_units": 256,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0.dev0",
+  "transformers_version": "4.32.1",
   "use_cache": false,
   "use_guided_attention_loss": true,
   "vocab_size": 81

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256b855c9145e6534084cbb68d83292996d26b806d59d1a6923e85acb5063ad8
-size 577878333
+oid sha256:93e5a5f37ace73955c35f4e0b967a935ba84603142e6deac6ac25d65748542b1
+size 577878778

tokenizer_config.json

@@ -3,7 +3,6 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "model_max_length": 600,
-  "normalize": false,
   "pad_token": "<pad>",
   "processor_class": "SpeechT5Processor",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5a3522be9faf61e3571f4d05d8183a3e7210eb22a4b4cec8a88feee70f543e
-size 4219
+oid sha256:923dc5caa4ebf32836d58c714b261dba448a1f77e612b4be61531ab220ef0d5e
+size 4664