返回模型
说明文档
<!-- 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 Large v3 1500 Epochs 2 - nullonesix
该模型是基于 distil-whisper/distil-small.en 在 atc 数据集上微调的版本。 在评估集上取得以下结果：
- Loss: 1.4151
- Wer: 39.2349
模型描述
更多信息待补充
预期用途与限制
更多信息待补充
训练与评估数据
更多信息待补充
训练过程
训练超参数
训练过程中使用了以下超参数：
- learning_rate: 1e-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: 500
- training_steps: 1500
- mixed_precision_training: Native AMP
训练结果
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.8313 | 3.5714 | 100 | 2.7177 | 74.1548 |
| 1.1366 | 7.1429 | 200 | 1.6407 | 63.0338 |
| 0.4394 | 10.7143 | 300 | 1.4737 | 47.4644 |
| 0.1686 | 14.2857 | 400 | 1.4481 | 46.3968 |
| 0.0761 | 17.8571 | 500 | 1.3707 | 40.8808 |
| 0.0452 | 21.4286 | 600 | 1.4051 | 38.5231 |
| 0.0188 | 25.0 | 700 | 1.4044 | 36.7883 |
| 0.0167 | 28.5714 | 800 | 1.4217 | 38.8345 |
| 0.0084 | 32.1429 | 900 | 1.4120 | 48.5765 |
| 0.0033 | 35.7143 | 1000 | 1.4151 | 39.2349 |
| 0.0022 | 39.2857 | 1100 | 1.4401 | 39.7242 |
| 0.0008 | 42.8571 | 1200 | 1.4591 | 39.5907 |
| 0.0007 | 46.4286 | 1300 | 1.4679 | 39.5907 |
| 0.0006 | 50.0 | 1400 | 1.4724 | 39.8577 |
| 0.0007 | 53.5714 | 1500 | 1.4737 | 39.7242 |
框架版本
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
nullonesix/distil-small.en
作者 nullonesix
automatic-speech-recognition
transformers
↓ 0
♥ 0
创建时间: 2024-07-10 22:48:36+00:00
更新时间: 2024-07-11 13:55:39+00:00
在 Hugging Face 上查看文件 (32)
.gitattributes
README.md
added_tokens.json
config.json
generation_config.json
ggml-distil-small.en.bin
ggml-distil-small.en.fp32.bin
merges.txt
model.fp32.safetensors
model.safetensors
normalizer.json
onnx/decoder_model.onnx
ONNX
onnx/decoder_model_merged.onnx
ONNX
onnx/decoder_model_merged_quantized.onnx
ONNX
onnx/decoder_model_quantized.onnx
ONNX
onnx/decoder_with_past_model.onnx
ONNX
onnx/decoder_with_past_model_quantized.onnx
ONNX
onnx/encoder_model.onnx
ONNX
onnx/encoder_model_quantized.onnx
ONNX
original-model.bin
original-model.fp32.bin
preprocessor_config.json
pytorch_model.bin
pytorch_model.fp32.bin
runs/Jul11_09-17-52_dpm4/events.out.tfevents.1720703894.dpm4.408810.0
runs/Jul11_09-17-52_dpm4/events.out.tfevents.1720706132.dpm4.408810.1
runs/events.out.tfevents.1701442148.t1v-n-10629e19-w-0.36003.0.v2
special_tokens_map.json
tokenizer.json
tokenizer_config.json
training_args.bin
vocab.json