kevinschweikert
Hey folks,
i am trying to get Membrane and Whisper working together. For now, the goal is, to use Mebrane so stream a file into Whisper. I worked on the following Livebook but cannot figure out, why Whisper is not correctly transcribing.
When i pipe the output of the converter into portaudio it is very noisy. When i set the converter to s16le the PortAudio audio sounds fine! But when i use :f32le and write it to a PCM file and import it into Audacity, it sounds fine again, despite the PortAudio Sink is not.
Either way, Whisper is not translating correctly. Can you help me out, where the issue could be?
Mix.install(
[
{:membrane_core, "~> 0.12.7"},
{:membrane_file_plugin, "~> 0.15.0"},
{:membrane_mp4_plugin, "~> 0.27.0"},
{:membrane_fake_plugin, "~> 0.10.0"},
{:membrane_raw_audio_format, "~> 0.11.0"},
{:membrane_ffmpeg_swresample_plugin,
git: "https://github.com/membraneframework/membrane_ffmpeg_swresample_plugin",
branch: "master"},
{:membrane_aac_plugin, "~> 0.15.0"},
{:membrane_aac_fdk_plugin, "~> 0.15.1"},
{:membrane_portaudio_plugin, "~> 0.16.1"},
{:kino_bumblebee, "~> 0.3.0"},
{:exla, "~> 0.5.1"}
],
config: [nx: [default_backend: EXLA.Backend], membrane_core: [logger: [verbose: false]]]
)
#dependecies:
brew install fdk-aac
brew install portaudio
model = "tiny"
{:ok, model_info} = Bumblebee.load_model({:hf, "openai/whisper-#{model}"})
{:ok, featurizer} = Bumblebee.load_featurizer({:hf, "openai/whisper-#{model}"})
{:ok, tokenizer} = Bumblebee.load_tokenizer({:hf, "openai/whisper-#{model}"})
{:ok, generation_config} = Bumblebee.load_generation_config({:hf, "openai/whisper-#{model}"})
generation_config = Bumblebee.configure(generation_config, max_new_tokens: 100)
generation_config = %{
generation_config
| forced_token_ids: [
# tell whisper that spoken text is german
{1, Bumblebee.Tokenizer.token_to_id(tokenizer, "<|de|>")},
{2, Bumblebee.Tokenizer.token_to_id(tokenizer, "<|transcribe|>")}
]
}
serving =
Bumblebee.Audio.speech_to_text(model_info, featurizer, tokenizer, generation_config,
compile: [batch_size: 1],
defn_options: [compiler: EXLA]
)
Nx.Serving.start_link(serving: serving, name: WhisperServing)
defmodule WhisperSink do
use Membrane.Sink
require Logger
def_input_pad(:input, demand_unit: :buffers, accepted_format: _any)
@impl true
def handle_playing(_ctx, state) do
{[demand: :input], state}
end
@impl true
def handle_write_list(:input, buffers, _ctx, state) do
for buffer <- buffers do
data =
buffer.payload
|> Nx.from_binary(:f32)
Logger.info(inspect(Nx.Serving.batched_run(WhisperServing, data)))
end
{[demand: {:input, length(buffers)}], state}
end
end
defmodule Pipeline do
use Membrane.Pipeline
@in_file "/path/to/video.mp4"
@impl true
def handle_init(_context, _opts) do
structure = [
child(:file_source, %Membrane.File.Source{location: @in_file, seekable?: true})
|> child(:demuxer, %Membrane.MP4.Demuxer.ISOM{optimize_for_non_fast_start?: true})
|> via_out(Pad.ref(:output, 2))
|> child(:depayloader_audio, Membrane.MP4.Depayloader.AAC)
|> child(:audio_parser, %Membrane.AAC.Parser{
in_encapsulation: :none,
out_encapsulation: :ADTS
})
|> child(:aac_decoder, Membrane.AAC.FDK.Decoder)
|> child(:converter, %Membrane.FFmpeg.SWResample.Converter{
output_stream_format: %Membrane.RawAudio{
sample_format: :f32le,
sample_rate: 16_000,
channels: 1
}
})
# |> child(:speaker, Membrane.PortAudio.Sink),
|> child(:whisper, WhisperSink),
get_child(:demuxer)
|> via_out(Pad.ref(:output, 1))
|> child(:fake, Membrane.Fake.Sink.Buffers)
]
{[spec: structure, playback: :playing], %{}}
end
@impl true
def handle_element_end_of_stream(:file_sink, _pad, _ctx_, _state) do
IO.inspect("terminate")
{[terminate: :normal], nil}
end
@impl true
def handle_element_end_of_stream(_child, _pad, _ctx, _state) do
{[], nil}
end
def handle_child_notification(notification, _element, _context, state) do
# dbg(notification)
{[], state}
end
end
{:ok, _, _} = Pipeline.start_link()
Trending in Questions
Hey guys,
I’ve got a huge CSV ( around 10 GB ) that needs to be processed hourly
Do you guys have any suggestions what is the best prac...
New
Hello!
Could someone please give me a help/sample code, how to delete a file from s3 using waffle/waffle_ecto from Phoenix app.
I creat...
New
I’m seeing that a list inside a Kino.DataTable will be interpreted as a charlist, even if the Kino.configure() is set to charlists: :as_l...
New
Anyone here using Honeybadger?
My Honeybadger account is being overwhelmed with noise from some bots. Seeing a lot of
Bandit.HTTPError...
New
So my question is quite simple and i have found no conclusive answer on forum, google or AI.
Should we use :erlang.float for Integer to ...
New
Hi, I’ve just set up an application with ash_authentication. There is only magic link strategy for now, so there is no confirmation add o...
New
If a change or preparation module uses Ash.Changeset.get_argument/2 or Ash.Query.get_argument/2 (or any of the other get_argument functio...
New
Other Trending Topics
I am happy to introduce the very α version of the new programming language compiled to BEAM.
Welcome Cure.
It has literally three kille...
New
Hobbes is a low-level distributed database for the Elixir programming language.
Hobbes provides a simple, safe, and scalable storage lay...
New
Beam Bots (or just BB for short) is a framework for building fault-tolerant robotics applications in Elixir using familiar OTP patterns. ...
New
ExRatatui lets you cook up rich terminal UIs in Elixir, powered by Rust’s ratatui via Rustler NIFs. Build interactive terminal applicatio...
New
Hello everyone. After busy few months I am happy to announce v0.1.0 of Emerge & Solve.
They are GUI (Emerge) and State management (S...
New
Corex is an accessible, unstyled UI component library for Phoenix that integrates Zag.js state machines using Vanilla JavaScript and Live...
New
Categories:
Sub Categories:
Forums
Popular Tags
- #ecto
- #liveview
- #troubleshooting
- #learning-elixir
- #deployment
- #library
- #erlang
- #testing
- #genserver
- #mix
- #absinthe
- #remote-other
- #otp
- #plug
- #how-to-question
- #macros
- #postgres
- #elixirconf
- #channels
- #exunit
- #discussion
- #code-sync
- #javascript
- #podcasts
- #onsite
- #dialyzer
- #docker
- #authentication
- #umbrella
- #full-time-contract
- #podcasts-by-brainlid
- #ecto-query
- #blog-post
- #elixir-ls
- #elixirconf-us
- #ai
- #phoenix_html
- #iex
- #graphql
- #genstage
- #websockets
- #supervisor
- #advent-of-code
- #distillery
- #processes
- #api
- #forms
- #hex
- #security
- #metaprogramming










Showing Posts 1 to 4- Show Best Posts
- Show All (oldest first)
- Show All (newest first)
mat-hek
Hi there, I’ll look into the converter & port audio issue. Regarding speech-to-text, have you tried this example?
kevinschweikert
Hi @mat-hek,
oh wow, thanks for the LiveBook example! I did not find it. After some trial and error and the membrane_transcription repo from @lawik i found out, that i obviously need to create a buffer, otherwise the length of the
Membrane.Buffer.payloadis to small for Whisper. The example would have saved me some timeI currently got this to work with a Whisper Serving startet in the Supervision tree and used manual demand. Otherwise the buffer would be too big for the Whisper model, because it can only handle a maximum chunk of 30s.
Again, thank you for your help!
mat-hek
Yeah, we’ll make those livebooks more discoverable. If the payload is too small/big, you can just concat/split it in the WhisperSink as well
However, to use automatic demands, you’d also have to move the logic from the task to the element or 
awaiton the task - otherwise, you can be flooded with dataBTW, you can use functions from Membrane.RawAudio — Membrane: raw audio format v0.12.3 instead of hardcoding sample rate & friends. Happy hacking
mat-hek
PortAudio bug fixed in Release v0.16.2 · membraneframework/membrane_portaudio_plugin · GitHub