অডিও বোঝার

# Install PyTorch & other libraries
pip install torch accelerate

# Install the transformers library
pip install "transformers>=5.10.1"

MODEL_ID = "google/gemma-4-E2B-it" # @param ["google/gemma-4-E2B-it","google/gemma-4-E4B-it", "google/gemma-4-12B-it"]

from transformers import pipeline

pipe = pipeline(
    task="any-to-any",
    model=MODEL_ID,
    device_map="auto",
    dtype="auto"
)

config.json:   0%|          | 0.00/4.95k [00:00<?, ?B/s]
model.safetensors:   0%|          | 0.00/10.2G [00:00<?, ?B/s]
Loading weights:   0%|          | 0/1951 [00:00<?, ?it/s]
generation_config.json:   0%|          | 0.00/208 [00:00<?, ?B/s]
processor_config.json:   0%|          | 0.00/1.69k [00:00<?, ?B/s]
chat_template.jinja:   0%|          | 0.00/17.3k [00:00<?, ?B/s]
tokenizer_config.json:   0%|          | 0.00/2.10k [00:00<?, ?B/s]
tokenizer.json:   0%|          | 0.00/32.2M [00:00<?, ?B/s]

Transcribe the following speech segment in {LANGUAGE} into {LANGUAGE} text.

Follow these specific instructions for formatting the answer:
*   Only output the transcription, with no newlines.
*   When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three.

from transformers import GenerationConfig
config = GenerationConfig.from_pretrained(MODEL_ID)
config.max_new_tokens = 64
gen_kwargs = dict(generation_config=config)

RESOURCE_URL_PREFIX = "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/apps/sample-data/"

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
            #{"type": "text", "text": "Transcribe the following speech segment in English into English text. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
            {"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal1.wav"},
        ]
    }
]

outputs = pipe(messages, return_full_text=False, generate_kwargs=gen_kwargs)
print(outputs[0]['generated_text'])

I woke up early today feeling really fresh the morning light was beautiful and I enjoyed a nice cup of coffee<turn|>

from transformers import GenerationConfig
config = GenerationConfig.from_pretrained(MODEL_ID)
config.max_new_tokens = 1024
gen_kwargs = dict(generation_config=config)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Give me a concise overview of these audio files."},
            {"type": "text", "text": "journal1:"},
            {"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal1.wav"},
            {"type": "text", "text": "journal2:"},
            {"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal2.wav"},
            {"type": "text", "text": "journal3:"},
            {"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal3.wav"},
            {"type": "text", "text": "journal4:"},
            {"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal4.wav"},
            {"type": "text", "text": "journal5:"},
            {"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal5.wav"},
        ]
    }
]

outputs = pipe(messages, return_full_text=False, generate_kwargs=gen_kwargs)
print(outputs[0]['generated_text'])

Here is a concise overview of each audio file:

**journal1:** The speaker describes a fresh and peaceful day, enjoying a cup of coffee.
**journal2:** The speaker had a perfect day at the park, including a walk and watching cherry blossoms.
**journal3:** The speaker finished the day with a good book, feeling grateful for simple moments.
**journal4:** The speaker returned from work and noted the beautiful night sky and a clear view from the train.
**journal5:** The speaker had a great lunch with an old friend, which was a pleasant way to catch up and made their day.
<turn|>

Transcribe the following speech segment in {SOURCE_LANGUAGE}, then translate it into {TARGET_LANGUAGE}.
When formatting the answer, first output the transcription in {SOURCE_LANGUAGE}, then one newline, then output the string '{TARGET_LANGUAGE}: ', then the translation in {TARGET_LANGUAGE}.

from transformers import GenerationConfig
config = GenerationConfig.from_pretrained(MODEL_ID)
config.max_new_tokens = 64
gen_kwargs = dict(generation_config=config)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Transcribe the following speech segment in English, then translate it into Korean. When formatting the answer, first output the transcription in English, then one newline, then output the string 'Korean: ', then the translation in Korean."},
            {"type": "audio", "audio": "https://ai.google.dev/gemma/docs/audio/roses-are.wav"},
        ]
    }
]

outputs = pipe(messages, return_full_text=False, generate_kwargs=gen_kwargs)
print(outputs[0]['generated_text'])

Roses are red, violets are blue.
Korean: 장미는 빨갛고, 제비꽃은 파랗다.<turn|>

pip install ipywebrtc

from google.colab import output
output.enable_custom_widget_manager()

from ipywebrtc import AudioRecorder, CameraStream

camera = CameraStream(constraints={'audio': True,'video':False})
recorder = AudioRecorder(stream=camera)
recorder

AudioRecorder(audio=Audio(value=b'', format='webm'), stream=CameraStream(constraints={'audio': True, 'video': …

with open('/content/recording.webm', 'wb') as f:
    f.write(recorder.audio.value)
!ffmpeg -i /content/recording.webm /content/recording.wav -y

ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
  built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
  configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
  libavutil      56. 70.100 / 56. 70.100
  libavcodec     58.134.100 / 58.134.100
  libavformat    58. 76.100 / 58. 76.100
  libavdevice    58. 13.100 / 58. 13.100
  libavfilter     7.110.100 /  7.110.100
  libswscale      5.  9.100 /  5.  9.100
  libswresample   3.  9.100 /  3.  9.100
  libpostproc    55.  9.100 / 55.  9.100
Input #0, matroska,webm, from '/content/recording.webm':
  Metadata:
    encoder         : Chrome
  Duration: 00:00:03.00, start: 0.000000, bitrate: 132 kb/s
  Stream #0:0(eng): Audio: opus, 48000 Hz, mono, fltp (default)
Stream mapping:
  Stream #0:0 -> #0:0 (opus (native) -> pcm_s16le (native))
Press [q] to stop, [?] for help
Output #0, wav, to '/content/recording.wav':
  Metadata:
    ISFT            : Lavf58.76.100
  Stream #0:0(eng): Audio: pcm_s16le ([1][0][0][0] / 0x0001), 48000 Hz, mono, s16, 768 kb/s (default)
    Metadata:
      encoder         : Lavc58.134.100 pcm_s16le
size=     287kB time=00:00:02.99 bitrate= 783.7kbits/s speed=79.4x    
video:0kB audio:287kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.026552%

from transformers import GenerationConfig
config = GenerationConfig.from_pretrained(MODEL_ID)
config.max_new_tokens = 64
gen_kwargs = dict(generation_config=config)

messages = [{
  "role": "user",
  "content": [
    {"type": "text", "text": "Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
    {"type": "audio", "audio": "/content/recording.wav"},
  ]
}]

outputs = pipe(messages, return_full_text=False, generate_kwargs=gen_kwargs)
print(outputs[0]['generated_text'])

How can I get to the station?<turn|>

messages = [{
  "role": "user",
  "content": [
    {"type": "text", "text": "Transcribe the following speech segment in English, then translate it into Korean. When formatting the answer, first output the transcription in English, then one newline, then output the string 'Korean: ', then the translation in Korean."},
    {"type": "audio", "audio": "/content/recording.wav"},
  ]
}]

outputs = pipe(messages, return_full_text=False, generate_kwargs=gen_kwargs)
print(outputs[0]['generated_text'])

How can I get to the station?
Korean: 역에 어떻게 가나요?<turn|>