openslr/librispeech_asr
Viewer • Updated • 585k • 109k • 225
How to use sanchit-gandhi/wav2vec2-2-rnd-grid-search with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="sanchit-gandhi/wav2vec2-2-rnd-grid-search") # Load model directly
from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq
tokenizer = AutoTokenizer.from_pretrained("sanchit-gandhi/wav2vec2-2-rnd-grid-search")
model = AutoModelForSpeechSeq2Seq.from_pretrained("sanchit-gandhi/wav2vec2-2-rnd-grid-search")YAML Metadata Error:"model-index[0].name" is not allowed to be empty
This model was trained from scratch on the librispeech_asr dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.9006 | 1.68 | 1500 | 6.9507 | 2.0097 |
| 6.9503 | 3.36 | 3000 | 6.9475 | 2.0097 |