Automatic Speech Recognition
Transformers
PyTorch
Armenian
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use arampacha/whisper-large-hy-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use arampacha/whisper-large-hy-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="arampacha/whisper-large-hy-2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("arampacha/whisper-large-hy-2") model = AutoModelForSpeechSeq2Seq.from_pretrained("arampacha/whisper-large-hy-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from arampacha/whisper-large-hy-2: direct link, hf CLI and curl.
- Browser
- Download file 1.79 kB
-
https://huggingface.co/arampacha/whisper-large-hy-2/resolve/main/README.md
- Command line
-
hf download hf://arampacha/whisper-large-hy-2/README.md
-
curl -L -o README.md https://huggingface.co/arampacha/whisper-large-hy-2/resolve/main/README.md
1.79 kB
metadata
language:
- hy
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
- google/fleurs
model-index:
- name: whisper-base-hy
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: hy-AM
split: test
args: hy-AM
metrics:
- name: Wer
type: wer
value: 19.986894
whisper-base-hy
This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1806
- eval_wer: 19.9869
- eval_runtime: 1358.6954
- eval_samples_per_second: 0.292
- eval_steps_per_second: 0.074
- epoch: 13.33
- step: 3000
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- training_steps: 4000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2