Ouwen
/

whisper-small-hi

Automatic Speech Recognition

hf-asr-leaderboard

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Ouwen commited on Mar 24

Commit

be66719

•

1 Parent(s): f5bfa1a

End of training

Files changed (2) hide show

README.md +8 -2
generation_config.json +1 -0

README.md CHANGED Viewed

@@ -43,10 +43,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - 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
 ### Framework versions
 - Transformers 4.40.0.dev0

 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- training_steps: 10
 - mixed_precision_training: Native AMP
+### Training results
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| No log        | 10.0  | 10   | 1.1995          | 68.6047 |
 ### Framework versions
 - Transformers 4.40.0.dev0

generation_config.json CHANGED Viewed

@@ -160,6 +160,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,

     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "hi",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,