End of training

README.md

@@ -12,7 +12,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: Whisper-Small-SW-SWAHILI
+- name: ASR_FROM_C3
   results:
   - task:
       name: Automatic Speech Recognition
@@ -26,18 +26,18 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 28.921534818493228
+      value: 15.699933328735316
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper-Small-SW-SWAHILI
+# ASR_FROM_C3
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4235
-- Wer: 28.9215
+- Loss: 0.2158
+- Wer: 15.6999
 
 ## Model description
 
@@ -63,15 +63,14 @@ The following hyperparameters were used during training:
 - 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: 2
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.2925        | 0.8684 | 2000 | 0.4415          | 30.5814 |
-| 0.1532        | 1.7369 | 4000 | 0.4235          | 28.9215 |
+| 0.1344        | 0.8684 | 2000 | 0.2158          | 15.6999 |
 
 
 ### Framework versions

config.json

@@ -41,7 +41,7 @@
   "scale_embedding": false,
   "torch_dtype": "float32",
   "transformers_version": "4.52.4",
-  "use_cache": true,
+  "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

generation_config.json

@@ -1,167 +1,17 @@
 {
-  "alignment_heads": [
-    [
-      5,
-      3
-    ],
-    [
-      5,
-      9
-    ],
-    [
-      8,
-      0
-    ],
-    [
-      8,
-      4
-    ],
-    [
-      8,
-      7
-    ],
-    [
-      8,
-      8
-    ],
-    [
-      9,
-      0
-    ],
-    [
-      9,
-      7
-    ],
-    [
-      9,
-      9
-    ],
-    [
-      10,
-      5
-    ]
-  ],
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
-  "is_multilingual": true,
   "lang_to_id": {
-    "<|af|>": 50327,
-    "<|am|>": 50334,
-    "<|ar|>": 50272,
-    "<|as|>": 50350,
-    "<|az|>": 50304,
-    "<|ba|>": 50355,
-    "<|be|>": 50330,
-    "<|bg|>": 50292,
-    "<|bn|>": 50302,
-    "<|bo|>": 50347,
-    "<|br|>": 50309,
-    "<|bs|>": 50315,
-    "<|ca|>": 50270,
-    "<|cs|>": 50283,
-    "<|cy|>": 50297,
-    "<|da|>": 50285,
-    "<|de|>": 50261,
-    "<|el|>": 50281,
-    "<|en|>": 50259,
-    "<|es|>": 50262,
-    "<|et|>": 50307,
-    "<|eu|>": 50310,
-    "<|fa|>": 50300,
-    "<|fi|>": 50277,
-    "<|fo|>": 50338,
-    "<|fr|>": 50265,
-    "<|gl|>": 50319,
-    "<|gu|>": 50333,
-    "<|haw|>": 50352,
-    "<|ha|>": 50354,
-    "<|he|>": 50279,
-    "<|hi|>": 50276,
-    "<|hr|>": 50291,
-    "<|ht|>": 50339,
-    "<|hu|>": 50286,
-    "<|hy|>": 50312,
-    "<|id|>": 50275,
-    "<|is|>": 50311,
-    "<|it|>": 50274,
-    "<|ja|>": 50266,
-    "<|jw|>": 50356,
-    "<|ka|>": 50329,
-    "<|kk|>": 50316,
-    "<|km|>": 50323,
-    "<|kn|>": 50306,
-    "<|ko|>": 50264,
-    "<|la|>": 50294,
-    "<|lb|>": 50345,
-    "<|ln|>": 50353,
-    "<|lo|>": 50336,
-    "<|lt|>": 50293,
-    "<|lv|>": 50301,
-    "<|mg|>": 50349,
-    "<|mi|>": 50295,
-    "<|mk|>": 50308,
-    "<|ml|>": 50296,
-    "<|mn|>": 50314,
-    "<|mr|>": 50320,
-    "<|ms|>": 50282,
-    "<|mt|>": 50343,
-    "<|my|>": 50346,
-    "<|ne|>": 50313,
-    "<|nl|>": 50271,
-    "<|nn|>": 50342,
-    "<|no|>": 50288,
-    "<|oc|>": 50328,
-    "<|pa|>": 50321,
-    "<|pl|>": 50269,
-    "<|ps|>": 50340,
-    "<|pt|>": 50267,
-    "<|ro|>": 50284,
-    "<|ru|>": 50263,
-    "<|sa|>": 50344,
-    "<|sd|>": 50332,
-    "<|si|>": 50322,
-    "<|sk|>": 50298,
-    "<|sl|>": 50305,
-    "<|sn|>": 50324,
-    "<|so|>": 50326,
-    "<|sq|>": 50317,
-    "<|sr|>": 50303,
-    "<|su|>": 50357,
-    "<|sv|>": 50273,
-    "<|sw|>": 50318,
-    "<|ta|>": 50287,
-    "<|te|>": 50299,
-    "<|tg|>": 50331,
-    "<|th|>": 50289,
-    "<|tk|>": 50341,
-    "<|tl|>": 50348,
-    "<|tr|>": 50268,
-    "<|tt|>": 50351,
-    "<|uk|>": 50280,
-    "<|ur|>": 50290,
-    "<|uz|>": 50337,
-    "<|vi|>": 50278,
-    "<|yi|>": 50335,
-    "<|yo|>": 50325,
-    "<|zh|>": 50260
+    "sw": 50357
   },
   "language": "sw",
-  "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": [],
   "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.52.4",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa25fc5b77f8c3e57f604473cf4bd35f52d923c04509c0e887ff2d84b6d323d
+oid sha256:4f0658bacea103517a8116ce163f7175eb5f69abe585f72ca966a49b1b2618fc
 size 966995080

runs/Aug11_05-57-33_fdc595d0574b/events.out.tfevents.1754891856.fdc595d0574b.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a43d0d5de879d79a94582fb17b5b0116ead15be81dea5768b4a7b796f222e9
+size 6549

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477d35287b2e29852132f5582cd65cd10e4c08e416fe5b54a67630453eab8b35
+oid sha256:2ddd7fd327eea9e40930d64ae1aca3b22eceb638ae13308746e0ded8608762d4
 size 5432