End of training

README.md

@@ -11,7 +11,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: Whisper Small Hi - Sanchit Gandhi
+- name: Whisper Small
   results:
   - task:
       name: Automatic Speech Recognition
@@ -23,18 +23,18 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 35.83130951004202
+      value: 37.234493658687015
 ---
 
 <!-- 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 Hi - Sanchit Gandhi
+# Whisper Small
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the AfriVoice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8767
-- Wer: 35.8313
+- Loss: 1.0151
+- Wer: 37.2345
 
 ## Model description
 
@@ -62,15 +62,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 20
+- num_epochs: 40
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.0665        | 8.1633  | 1000 | 0.7047          | 36.8683 |
-| 0.0023        | 16.3265 | 2000 | 0.8767          | 35.8313 |
+| 0.1977        | 8.1301  | 500  | 0.7429          | 41.9683 |
+| 0.0059        | 16.2602 | 1000 | 0.9167          | 38.4064 |
+| 0.001         | 24.3902 | 1500 | 0.9849          | 37.3501 |
+| 0.0007        | 32.5203 | 2000 | 1.0151          | 37.2345 |
 
 
 ### Framework versions

generation_config.json

@@ -48,16 +48,6 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      null
-    ],
-    [
-      2,
-      50359
-    ]
-  ],
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,
@@ -160,6 +150,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "lingala",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -256,6 +247,7 @@
     50361,
     50362
   ],
+  "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9257ed63e28728a72a869008e50a42e0c7e85ef5bfc7325029d88e555a77c87f
+oid sha256:bd3eef14dcb4e427a0b71fe7a92f40f71dc89c0f157471c2bd970487925446dd
 size 966995080