![]() ![]() ![]() But thankfully, onboarding is extremely funny and engaging. It is much more than a speech-to-text converter. The main thing you have to know is that it is a standalone software rather than a web service. To locate it, you need to go to the footer of the homepage and look for it under “Services.”ĭescript welcomed me by name (which was a nice coincidence). ![]() Rev also has a 14-day trial of its paid plan. I got a bill for $1.25 with a discount that resulted in a total of $0.00. You can transcribe the first audio file (up to 45 minutes) for free. As a result, some paragraphs didn’t make much sense, while others were fine. Some words were missing, while others were misrecognized. Poor audio with city noise was a bit too much for Rev. You also have the option to place an order for human transcriptions. Unique featuresīesides auto-generated transcripts, Rev offers live captions for Zoom meetings. You might get an impression that it was designed by an accounting team (as opposed to Descript that comes next in this roundup). One personal remark is that it felt a little too “cold” to use since I saw things like “Place Order,” “Billing,” and “Invoice” way too often. I found the interface easy to navigate as well. You can import up to three files and record 290 minutes of meetings before you need to upgrade (as of April 2023). You can start for free and upgrade to a paid plan later. Like a student still scribbling on a test paper while passing it to the teacher. One thing I found is that after it notified the transcriptions were ready, it might still do something in the background (adjust time stamps, tag speakers, etc.). But I can’t blame any tool for not picking up “Ahrefs” or “Tim Soulo” 100% of the time. I got decent results, but there was a lot to edit too. But you can also import a video/audio file or record audio right in the app.īesides, you can connect your calendar to never miss a meeting. ![]() What stands out from the rest is the app’s ability to record online meetings and transcribe them-simply by pasting the meeting URL. It is easy to set up, has an intuitive interface, and offers clear pricing. It is far from perfect, but I don’t want to translate, I want to extract keywords.Otter was one of the most frequently mentioned solutions when we asked for suggestions on Twitter and in the Ahrefs community. Inference took 678.371s for 1210.247s audio file.Īnd here is the raw result, some parts are ok, and some are really funny translations. There are language packs, but I only tested english. The system is not on the cloud, it runs on your machine. Now I need to glue ffmpeg and deepspeech with Elixir to have the beginning of a working solution. And with a compatible card, it is possible to run on GPU It looks promising and is even faster than expected. Inference took 1.562s for 2.590s audio file. Loading language model from files deepspeech-0.5.1-models/lm.binary deepspeech-0.5.1-models/trie 01:53:25.693211: E tensorflow/core/framework/op_:1325] OpKernel ('op: "WrapDatasetVariant" device_type: "CPU"') for unknown op: WrapDatasetVariant 01:53:25.693200: E tensorflow/core/framework/op_:1325] OpKernel ('op: "WrapDatasetVariant" device_type: "GPU" host_memory_arg: "input_handle" host_memory_arg: "output_handle"') for unknown op: WrapDatasetVariant 01:53:25.693187: E tensorflow/core/framework/op_:1325] OpKernel ('op: "UnwrapDatasetVariant" device_type: "CPU"') for unknown op: UnwrapDatasetVariant 01:53:25.693154: E tensorflow/core/framework/op_:1325] OpKernel ('op: "UnwrapDatasetVariant" device_type: "GPU" host_memory_arg: "input_handle" host_memory_arg: "output_handle"') for unknown op: UnwrapDatasetVariant Loading model from file deepspeech-0.5.1-models/output_graph.pbmm For those interested in the subject, I did some basic tests with $ deepspeech -model deepspeech-0.5.1-models/output_graph.pbmm -alphabet deepspeech-0.5.1-models/alphabet.txt -lm deepspeech-0.5.1-models/lm.binary -trie deepspeech-0.5.1-models/trie -audio audio/8455-210777-0068.wav ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |