whisper-hindi-small

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: vasista22/whisper-hindi-small
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: whisper-hindi-small
+  results: []
+---
+
+<!-- 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-hindi-small
+
+This model is a fine-tuned version of [vasista22/whisper-hindi-small](https://huggingface.co/vasista22/whisper-hindi-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1972
+- Wer: 19.6516
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.75e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 250
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.1187        | 0.9   | 250  | 0.1903          | 24.5993 |
+| 0.0532        | 1.8   | 500  | 0.1903          | 22.5784 |
+| 0.0218        | 2.7   | 750  | 0.1930          | 20.1394 |
+| 0.0064        | 3.6   | 1000 | 0.1972          | 19.6516 |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "transformers_version": "4.34.0",
+  "use_cache": false
+}