For a while now I wondered how I would ever manage to transcribe my podcast episodes. Today I stumbled upon the CMUSphinx Tutorial For Developers and I discovered that `pocketsphinx` was available for my system! I installed it, and the US English language model, `pocketsphinx-en-us`.
CMUSphinx Tutorial For Developers
Convert an MP3 file to WAV 16kHz 16-bit mono:
ffmpeg -i 01-halberds-and-helmets.mp3 -acodec pcm_s16le \
-ac 1 -ar 16000 01-halberds-and-helmets.wav
Process it:
pocketsphinx_continuous -infile 01-halberds-and-helmets.wav \
-hmm /usr/share/pocketsphinx/model/en-us/en-us \
-lm /usr/share/pocketsphinx/model/en-us/en-us.lm.bin \
-dict /usr/share/pocketsphinx/model/en-us/cmudict-en-us.dict \
> 01-halberds-and-helmets.txt
Listen along, if you want to: 01-halberds-and-helmets.mp3.
Here’s what `pocketsphinx` produces:
hello this is our next big thing and desist albert said helmet sport cause the first episode i want to talk about my game to the fairly simple i'm old school the indie game very simple rules so very special but it's mine and ten talking about it provides a framework for me to talk about all the games i like to play
Oh wow. This would require *a lot* of editing!
If I transcribe it, using the same linebreaks as above:
hello this is alex speaking and this is the halberds and helmets podcast first episode i want to talk about my game a fairly simple old school d and d game very simple rules it's not very special but it's mine and talking about it provides a framework for me to talk about all the other games i like to play
#Speech to Text
(Please contact me if you want to remove your comment.)
⁂
Thisten offers something for $0.10/min. They asked me for my credit card info before letting see the trial results. As I was skimming the Terms of Service, I noticed: “In the interest of resolving disputes between you and Thisten in the most expedient and cost effective manner, … you and Thisten agree that every dispute arising in connection with these Terms will be resolved by binding arbitration.
Temi offers something for $0.25/min. I was able to upload a file, provide an email address, and got a link back in a few seconds.
Hello, this is Alex speaking, and this is the Halberts and helmets podcast. The first episode, I want to talk about my game to fairly simple old school, the indie game, very simple rules. It’s not very special, but it’s mine. And I’m talking about, it provides a framework for me to talk about all the other games and like to play.
That’s pretty good! And they web app plays back the recording, showing you where you are in the transcript, allowing you to make changes as you listen along, fixing up things. It looks pretty good to me!
– Alex Schroeder 2020-07-01 09:57 UTC