41554 blogs · 4,504,310 posts Claim your blog

Record · corpus.blog/posts/01a0b5e4-93a6-7253-82f6-d46a941dc204

Breaking language barriers: Fine-tuning Whisper for Hindi

collabora.com · published 19 February 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at collabora.com Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 17
Words captured: 1,049

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://github.com/anoopkunchukuttan/indic_nlp_library/blob/4cead0ae6c78fe9a19a51ef679f586206df9c476/indicnlp/normalize/indic_normalize.py

github.com

https://wandb.ai/makaveli/whisper-hindi-scratch-default-tokenizer-webdataset?nw=nwusermakaveli

wandb.ai

https://www.collabora.com/news-and-blog/news-and-events/https://www.collabora.com/assets/images/blog/wer_plot.png

collabora.com

https://huggingface.co/collabora/whisper-tiny-hindi

huggingface.co

https://huggingface.co/collabora/whisper-base-hindi

huggingface.co

https://huggingface.co/collabora/whisper-small-hindi

huggingface.co

https://github.com/collabora/whisper-finetuning

github.com

https://huggingface.co/datasets/collabora/hindi-preprocessed-wds-full

huggingface.co

https://ai4bharat.iitm.ac.in/

ai4bharat.iitm.ac.in

https://ai4bharat.iitm.ac.in/datasets/shrutilipi

ai4bharat.iitm.ac.in

https://asr.iitm.ac.in/

asr.iitm.ac.in

https://asr.iitm.ac.in/dataset

asr.iitm.ac.in

https://foundation.mozilla.org/en/

foundation.mozilla.org

https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0

huggingface.co

https://huggingface.co/google

huggingface.co

https://huggingface.co/datasets/google/fleurs

huggingface.co

https://github.com/anoopkunchukuttan/indic_nlp_library

github.com