vasistalodagala/whisper-finetune
Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.
PythonMIT
Issues
- 3
finetune on commonvoice
#12 opened by cod3r0k - 0
dataset with segment metadata
#15 opened by lalimili6 - 1
- 4
fine-tuning does not seem to improve/converge
#11 opened by welliX - 3
pytorch_model.bin not getting saved
#13 opened by 25Varun - 6
Information On Batch Size And Learning Rate
#3 opened by mallorbc - 0
Multilingual Finetuning of Whisper
#10 opened by Lorenzoncina - 2
this isnt really an issue, just a question about fine tuning whisper to better recognize spoken names
#4 opened by silvacarl2 - 0
- 0
how to add a new language?
#8 opened by yfliao - 0
- 0
- 1
missing arguments
#1 opened by AYUSH27112021 - 5
- 1
Create LICENSE
#2 opened by mallorbc