Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
Generated from Trainer
Instructions to use Rithik101/WhispASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rithik101/WhispASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Rithik101/WhispASR")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Rithik101/WhispASR") model = AutoModelForSpeechSeq2Seq.from_pretrained("Rithik101/WhispASR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Rithik101/WhispASR: direct link, hf CLI and curl.
- Browser
- Download file 1.51 kB
-
https://huggingface.co/Rithik101/WhispASR/resolve/main/README.md
- Command line
-
hf download hf://Rithik101/WhispASR/README.md
-
curl -L -o README.md https://huggingface.co/Rithik101/WhispASR/resolve/main/README.md
1.51 kB
metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: openai/whisper-small
metrics:
- wer
model-index:
- name: checkpoints
results: []
datasets:
- ai4bharat/kathbath
language:
- hi
pipeline_tag: automatic-speech-recognition
checkpoints
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0775
- Wer: 54.4629
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.4636 | 0.0255 | 10 | 1.0775 | 54.4629 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1