ऑडियो को समझना

# Install PyTorch & other libraries
pip install torch accelerate

# Install the transformers library
pip install transformers

MODEL_ID = "google/gemma-4-E2B-it" # @param ["google/gemma-4-E2B-it","google/gemma-4-E4B-it", "google/gemma-4-31B-it", "google/gemma-4-26B-A4B-it"]

from transformers import AutoProcessor, AutoModelForMultimodalLM

model = AutoModelForMultimodalLM.from_pretrained(MODEL_ID, dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(MODEL_ID)

Loading weights:   0%|          | 0/2011 [00:00<?, ?it/s]

RESOURCE_URL_PREFIX = "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/Demos/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"},
        ]
    }
]

input_ids = processor.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True, return_dict=True,
        return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)

outputs = model.generate(**input_ids, max_new_tokens=64)

text = processor.batch_decode(
    outputs,
    skip_special_tokens=False,
    clean_up_tokenization_spaces=False
)
print(text[0])

<bos><|turn>user
Transcribe the following speech segment in its original language. 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.<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|>
<|turn>model
I woke up early today feeling really fresh the morning light was beautiful and I enjoyed a nice cup of coffee<turn|>

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"},
        ]
    }
]

input_ids = processor.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True, return_dict=True,
        return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)

outputs = model.generate(**input_ids, max_new_tokens=1024)

text = processor.batch_decode(
    outputs,
    skip_special_tokens=False,
    clean_up_tokenization_spaces=False
)
print(text[0])

<bos><|turn>user
Give me a concise overview of these audio files.journal1:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|>journal2:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|>journal3:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|>journal4:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|>journal5:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|>
<|turn>model
Here is a concise overview of the audio files:

**Journal 1:** The speaker felt refreshed, enjoyed a morning ride, a cup of coffee, and was generally happy.

**Journal 2:** The speaker spent the afternoon at the park, which was a perfect day for a walk, and enjoyed watching the cherry blossoms.

**Journal 3:** The speaker finished the day with a good book, feeling grateful for simple moments and ready for more.

**Journal 4:** The speaker returned from work, admiring the sunset, and enjoyed a clear view from the train.

**Journal 5:** The speaker had a great lunch with an old friend, enjoyed catching up, and felt happy about the day.<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": "https://ai.google.dev/gemma/docs/audio/roses-are.wav"},
        ]
    }
]

input_ids = processor.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True, return_dict=True,
        return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)

outputs = model.generate(**input_ids, max_new_tokens=64)

text = processor.batch_decode(
    outputs,
    skip_special_tokens=False,
    clean_up_tokenization_spaces=False
)
print(text[0])

<bos><|turn>user
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.<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|>
<|turn>model
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: 00:00:04.02, start: 0.000000, bitrate: 131 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=     383kB time=00:00:04.01 bitrate= 779.7kbits/s speed=60.6x    
video:0kB audio:382kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.019914%

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"},
  ]
}]

input_ids = processor.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True, return_dict=True,
        return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)

outputs = model.generate(**input_ids, max_new_tokens=64)

text = processor.batch_decode(
    outputs,
    skip_special_tokens=False,
    clean_up_tokenization_spaces=False
)
print(text[0])

<bos><|turn>user
Transcribe the following speech segment in its original language. 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.<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|>
<|turn>model
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"},
  ]
}]

input_ids = processor.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True, return_dict=True,
        return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)

outputs = model.generate(**input_ids, max_new_tokens=64)

text = processor.batch_decode(
    outputs,
    skip_special_tokens=False,
    clean_up_tokenization_spaces=False
)
print(text[0])

<bos><|turn>user
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.<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|>
<|turn>model
How can I get to the station?
Korean: 역에 어떻게 가나요?<turn|>