Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Instructions to use itsally/LibriSpeech with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use itsally/LibriSpeech with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="itsally/LibriSpeech")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("itsally/LibriSpeech") model = AutoModelForSpeechSeq2Seq.from_pretrained("itsally/LibriSpeech", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from itsally/LibriSpeech: direct link, hf CLI and curl.
- Browser
- Download file 1.53 kB
-
https://huggingface.co/itsally/LibriSpeech/resolve/main/README.md
- Command line
-
hf download hf://itsally/LibriSpeech/README.md
-
curl -L -o README.md https://huggingface.co/itsally/LibriSpeech/resolve/main/README.md
1.53 kB
metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- openslr/librispeech_asr
model-index:
- name: Fine Tune Whisper on LibriSpeech
results: []
Fine Tune Whisper on LibriSpeech
This model is a fine-tuned version of openai/whisper-small on the LibriSpeech dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2510
- eval_wer: 8.8067
- eval_runtime: 109.0599
- eval_samples_per_second: 1.834
- eval_steps_per_second: 0.229
- epoch: 20.0
- step: 1000
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: 16
- eval_batch_size: 8
- seed: 42
- 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
- training_steps: 5000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.52.0
- Pytorch 2.9.0+cu126
- Datasets 4.4.1
- Tokenizers 0.21.4