End of training

README.md

@@ -2,8 +2,9 @@
 language:
 - mn
 license: apache-2.0
-base_model: openai/whisper-small
+base_model: openai/whisper-tiny
 tags:
+- hf-asr-leaderboard
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_13_0
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Tiny Mn - Ochirsukh Batbold
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 13.0, Google Fleurs dataset.
 
 ## Model description
 
@@ -43,8 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 5
-- mixed_precision_training: Native AMP
+- training_steps: 3
 
 ### Training results
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 1.13.1+cu117
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cpu
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -147,7 +147,7 @@
     50362
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.2",
   "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -144,10 +144,11 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "max_initial_timestamp_index": 1,
+  "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
   "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -243,5 +244,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.38.2"
 }

merges.txt

@@ -1,4 +1,5 @@
 #version: 0.2
+Ġ t
 Ġ a
 Ġt h
 i n

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54949258c437ee373da926ac04154414455d0d4c8161f0d20c82828c20a423b5
+oid sha256:29486bafae1b91cbba6c0e7cbfa3a1f17d3cab5ec3c8db3d8b75f0e3d499f382
 size 151061672

runs/Mar14_12-53-13_UBOFFICE-ML1/events.out.tfevents.1710392040.UBOFFICE-ML1.1832.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffa5e924120ac024ff67e7f0f0bd83d156d84a129bd0a952b51037d06deab6e
+size 6711

special_tokens_map.json

@@ -111,14 +111,14 @@
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -132,7 +132,7 @@
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -5,7 +5,7 @@
     "50257": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40a0d185694cc56c2fc9fdd331de68ac9ab8b26f410400080e9347dee3b02fa
-size 4283
+oid sha256:717f54600188f1e180ae220c39fafbbb16faf8a99cd1ac7297c0411742bb2f9f
+size 5048