Search results

@porgate55555 Apparently, that doesn't work for me. I just get to a download page where it asks me if I want to download the script. Sorry. I don't know much about this.

I'll try that after Christmas. Thanks for replying.

@mei2 Do you mean I have to install programs on my local computer for Whisper to work? I thought it was a virtual environment since all sources used are uploaded online. Here's the settings at the address. Only change I make is No Translation. The address to the audio is the same as in the...

Thanks for replying. I tried inserting the code from the first part of the script as instructed by SamKook but I get the same message at the end: I don't use the locally installed files when using collab so why is this install problem happening? I do get a red mark at the side of the script...

Ahh! I see now. I was looking at the parameters at Run Whisper only. So I put all that code before this?: else: if not os.path.exists(audio_path): try: audio_path = uploaded_file if not os.path.exists(audio_path): raise ValueError("Input...

Thanks. But no, that's not how the default script on that address looked from what I remember. https://colab.research.google.com/github/meizhong986/WhisperJAV/blob/main/notebook/WhisperWithVAD_pro.ipynb#scrollTo=sos9vsxPkIN7 I'll check back when I've finished what I mention below. I'll try that...

Yeah. It's a difference in file size: 16 kb vs 69 or 70 kb. The settings for line division are off in Faster Whisper, some lines are very long (12 seconds) but I guess I can edit that later.

I'm afraid I don't understand the text about moving parts of the script in collab. The script is divided into #@markdown **Run Whisper** # @markdown Required settings: # Generate VAD timestamps # Add a bit of padding, and remove small gaps # If breaks are longer than chunk_threshold seconds...

Thanks. Yeah, I managed to find the command info here: https://github.com/Purfview/whisper-standalone-win/discussions/231 I can't seem to fix the Collab problem with recognizing too few lines. I've been told to upload mono tracks so I'm using the recommended ffmpeg command line to convert stereo...

Also, the old colab seems to need some help. I get really short scripts from it compared to Faster Whisper. A 3 hr video gives me 228 lines in colab and 1044 in Faster Whisper with Medium.

Are there parameters in Faster Whisper for using different versions? I didn't look that hard for command line parameters for Faster Whisper but what I found was just small, medium and large. This is what I use: faster-whisper-xxl.exe File.mp4 --language ja --task transcribe --model large...

Thanks, SamKook. No, I don't know anything about code or scripts, really. I never used source separation on the old Colab because it never worked. I'll see if I can use this. In the meantime I'll use the old Colab and Faster Whisper using the model Medium. The large model gives me SO many bad...

Could you help me with the error message I get? NameError Traceback (most recent call last) <ipython-input-6-1bc508f8c32b> in <cell line: 37>() 35 out_path = os.path.splitext(audio_path)[0] + ".srt" 36 out_path_pre = os.path.splitext(audio_path)[0] +...

Is the WhisperPro you refer to this: https://colab.research.google.com/github/ANonEntity/WhisperWithVAD/blob/main/WhisperWithVAD.ipynb I've tried FasterWhisper this week but haven't compared to the colab version yet. Thanks for all the new info. There's not all that much info on command strings...

The problem with Sup**v's 'newer' mosaic reduced files is that they use a smoothing step before finishing the process. It tends to make the mosaiced parts look 'unreal' or simply warped. I don't know how they're doing it but I wouldn't recommend keeping it up. I check their files and decide if I...

T28-546 Brutal Father Cumshot Training Using a Hypnosis App to Make a Daughter Compliant with Hoshina Ai I've been sitting on this translation for a month but I'm releasing it now. There's no Chinese translation for this video and I, as well as a friend of mine, really like this video. I...

Using the WhisperDesktop and the medium.bin from the link, I get a very large srt but with mostly music notes and one or two different lines of the same subtitle repeated ad nauseam. Maybe 20-30 lines of proper dialog in all. I'm trying with the large file now. If that doesn't work, I'll just...

So how do I actually download models from HuggingFace? The links lead to pages with lots of info on the models and there's a file section but there's no .bin to download like there is here: https://huggingface.co/datasets/ggerganov/whisper.cpp/tree/main For example...

Thanks. I'll look into that. I guess I can't run this on this computer since it can't run on CPU. I'll have to try it on my W10 computer with a fairly good graphics card with GPU.

So, if I use the web version of Whisper, how can I use different models? https://colab.research.google.com/github/ANonEntity/WhisperWithVAD/blob/main/WhisperWithVAD.ipynb#scrollTo=jh24lirNZnXT Unless someone makes a version of Whisper as a simple installation exe with a Windows GUI, I won't be...

I wouldn't know how to make that monofile with ffmpeg. I use Audacity to merge channels and encode as variable bitrate ogg for now. Better than mp3 in retaining information at the same bitrates. I use the webbased Whisper only. If I were to try and upload uncompressed files, I'd have to wait...

I've tried both stereo and mono and from what I can tell, I always get better results starting with a stereo file. It makes no difference if Whisper converts that stereo track into a mono track. My tests point to better results if the original track is in stereo. And for me there's pretty much...

Just a tip on Whisper about translation: Don't use it. Just choose No Translation and do that later in Google translate or DeepL translate (use Tor Browser so you don't get blocked for using up your free ratio (500.000 characters a month). You will need to separate the text from the timing...

I have increased volume with all three types of audio to text and if you don't go overboard with the volume increase it has always yielded better results. Amplification is also better than compression. Some software doesn't like clipping so you may have to think about that, too.

I did mention that mono tracks didn't work with Autosub and Vrew a few pages back and maybe someone claimed Whisper converts the track you upload to mono? Not sure. I have only uploaded one track in mono and that was from a Korean film where only the center channel of the 5.1 track contained...

I just ran a test with 0.1 as VAD_Threshold and the result was 993 lines with the same text. So stay away from such low VAD numbers. I'm currently trying VAD_Threshold 0.2.

If I use collab and set vad threshold to 0 or remove the number there, will it stop using VAD? I have heard some of the online programs' attempts at isolating voices and a lot of them do a very bad job, making the dialog more unclear. I don't see a version without VAD linked anywhere so I...

Okay. Autosub didn't give good results on mono audio. Neither does Vrew.

About Whisper. Does Whisper Collab really accept other formats than mp3? It's the format that is written on the audio_path: line and I can't find any info on audio formats that can be used in the help.

Whisper Colab seems to limit usage variably. Today, I could only process two 1 hr files before getting told I didn't have more GPU resources available. Trying to get as complete a result from the software for one specific video.

What are the usage limits on Whisper Colab? Are they time limited (24 hrs) or do I have to wait several days to use it with GPU again? Not going to use Pro version.

I get 573 lines with the full 2hr file now. When breaking it into two files I got 613 lines in total.

It is GPU. I don't have a GPU with lots of memory on this computer. Whisper converts the 2 hr files into something that is 2.9GB large and then goes on to find dialog. After running the audio it tells me I have number/220 and gives me a file of _ lines. This is the audio I use: SGV-018 Can I get...

I tried it with a 2 hr file and it only gave me 24 lines. Then I split it up in two and it gave me about 250 lines, translated, per file. It's about equal the amount I get from Vrew. Is there a way to get just Japanese subtitles? I'd like to try different subtitle translations based on those...

I don't recall seeing that one, but I haven't watched all the videos I've downloaded all the way through. In this one (CAWD-148) they are both shaved but they aren't being shaved. I've checked javlibrary for their videos together and can't find any thumbnails where I see them getting shaved...

A few actresses I've followed for a while have been shaved for most or all of their careers: Mikako Abe Ichika Matsumoto Saeko Matsushita These girls have probably been paipan since their first appearance (I haven't seen all of their videos): Ichigo Aoi has been paipan for most of her career...

Just a quick update: Don't use downsampled Mono with Vrew. I've only checked the Korean language extractor, but if you make it mono and 16Hz you'll get roughly a third less text in the file. I tried a mono file at 48Hz and it worked almost as well as an unadjusted stereo track. Amplify it in...

I have used Vrew a little and it finds more dialog than pyTranscriber (autosub) but it's not always more accurate. I thought it was more accurate with Korean since it uses a dedicated Korean api but I guess Google is superior in this case. How would one convert audio to female voice? Higher...

Thanks for posting that links. I don't use that kind of script language a lot. Do I just copy the section up top that begins with: "from huggingsound import SpeechRecognitionModel" and input the full input/output paths to the audio in the command prompt and it will do its work? I don't see any...

Only problem it's not available to download from a reputable source (yeah, I know...) so you have to pay to get it. But I found it on torrent as well.

I like her a lot and one video stands out to me: IPZ-519 The Innocent Lady's Dirty Campus Life - The Extreme Squirting Sex Of A Panty-less, Bra-less College Girl. It's full of humour and sex. A lot of her filmography is nonconsensual. IPZ-603, IPZ-620, IPZ-694, JUY-395.

Thanks! :)

This is part of the video which is available under the title Old pervert fucks his cute Japanese daughter, is a horny teen Link is HERE Capture attached. I know I've seen her before, and I even tried to identify the video by going by the male lead, his name is Saeyama Toshiki 冴山トシキ. She does...

Ths subs included are JUX-386. Please check before posting.

I don't think I could watch this. Sorry. Try pyTranscriber or Autosub_Gui (Link) to see if you can catch the Japanese dialog. Then use Deepl or Google translation.

I had a few more that were in the subitle packs. Download the 28.000 pack available in the subtitle thread. 28.000 subtitles pack Haruna Hana

Then I don't know what the problem is. I've checked the video at Javqt and both of the subtitles match the dialog.

I'm sorry but I can't help you with that. Have you checked whether the first subtitle of the script is in sync with the first line of dialog? Since the script I provided (Deepl translation) has similar timing to the other script, that shouldn't be the issue. If your video doesn't begin...

Here are two links: JavQT Deepl translation of the Chinese subtitles You can see that there's a clear difference. JavQT are not using a good translation program.

Hm... No such video. Either SSIS-008, SSIS-080, SSIS-088. I've found subtitles for SSIS-008 but not the others. 088 hasn't come out yet (2021-06-19). Please moderate your requests. I accept requests up to a limit, like two subtitles a month, but I can't provide subtitles unless they are...